© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13239
    Prev
    Next
    INDEX
    Explanations

    the word "cross" in various contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    61
    +0.11
    0.4%
    120
    +0.11
    0.4%
    1124
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1708
    +0.11
    0.03
    569
    +0.11
    0.03
    61
    +0.11
    0.02
    Negative Logits
    Estadio
    -0.50
    Dichloroethane
    -0.50
    BeforeMethod
    -0.47
    RetentionPolicy
    -0.46
    További
    -0.46
    ApiModel
    -0.46
    Père
    -0.46
    FlatAppearance
    -0.46
    EventQueue
    -0.45
    Danke
    -0.45
    POSITIVE LOGITS
     cross
    1.20
     CROSS
    1.20
    Cross
    1.17
    cross
    1.17
     jaya
    1.17
     Cross
    1.13
    CROSS
    1.11
     crosses
    1.09
     bandung
    1.04
     cros
    1.02
    Activations Density 0.055%

    No Known Activations