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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12948
    Prev
    Next
    INDEX
    Explanations

    names, specifically the name "Nick"

    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
    950
    +0.17
    0.7%
    122
    +0.15
    0.6%
    1034
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    950
    +0.17
    0.03
    122
    +0.15
    0.02
    1810
    +0.15
    0.02
    Negative Logits
     slanted
    -0.49
     cancerous
    -0.45
     slova
    -0.44
     granule
    -0.44
     blurring
    -0.43
     periodontal
    -0.42
     itemId
    -0.41
    importante
    -0.40
     orderId
    -0.40
    Davide
    -0.40
    POSITIVE LOGITS
     Nick
    1.51
     NICK
    1.45
    Nick
    1.43
    NICK
    1.20
     nick
    1.19
    nick
    0.98
     Nicholas
    0.98
     NICH
    0.94
    Nicholas
    0.93
     Nich
    0.86
    Activations Density 0.077%

    No Known Activations