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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 6431
    Prev
    Next
    INDEX
    Explanations

    references to coaches and their evaluations or opinions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bní
    -0.64
     محفوظة
    -0.63
    ंदीखरीदारी
    -0.60
    FromArgb
    -0.57
     civile
    -0.56
    Javadoc
    -0.54
     bekasi
    -0.53
     Declare
    -0.52
    WebControls
    -0.52
    šní
    -0.51
    POSITIVE LOGITS
     coaches
    0.95
     coaching
    0.93
     coach
    0.86
     Coach
    0.80
     Coaches
    0.80
    Coaching
    0.78
     coached
    0.77
     Coaching
    0.75
    Coaches
    0.74
    coach
    0.71
    Activations Density 0.135%

    No Known Activations