© 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. 18-RES-MATRYOSHKA-DC
    7. 101
    Prev
    Next
    INDEX
    Explanations

    statistics and descriptions from American football games.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
     sortes
    -0.56
    matig
    -0.55
     actors
    -0.52
    НИК
    -0.52
    cognised
    -0.52
     persons
    -0.51
     Globally
    -0.51
     prati
    -0.51
    ParallelGroup
    -0.51
     gez
    -0.51
    POSITIVE LOGITS
     coached
    1.02
     playoff
    0.93
     teammates
    0.93
     preseason
    0.91
     playing
    0.90
     played
    0.89
     teammate
    0.88
     unbeaten
    0.84
     coach
    0.84
     scoring
    0.84
    Activations Density 2.805%

    No Known Activations