© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 879
    Prev
    Next
    INDEX
    Explanations

    words related to downward trends or movements

    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
    897
    +0.16
    0.5%
    1376
    +0.10
    0.3%
    486
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    897
    +0.16
    0.03
    1081
    +0.10
    0.03
    200
    +0.10
    0.02
    Negative Logits
    ioutil
    -0.52
     initComponents
    -0.51
    homonymie
    -0.51
    PerformLayout
    -0.50
    бият
    -0.49
    enumii
    -0.49
    Cri
    -0.47
    TestTools
    -0.47
    Ciclo
    -0.47
    Mix
    -0.47
    POSITIVE LOGITS
     apprehen
    1.08
     ricardo
    1.05
     homeward
    1.05
     fup
    1.03
     stockholm
    1.03
     intersper
    1.01
     ftu
    0.99
     increa
    0.98
     encomp
    0.97
     siena
    0.95
    Activations Density 0.125%

    No Known Activations