© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 1288
    Prev
    Next
    INDEX
    Explanations

    text describing a quarterback who can run and improvise

    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
    ragos
    -0.52
     tạm
    -0.51
     gostar
    -0.49
    mony
    -0.49
     Roskov
    -0.49
    ORAGE
    -0.48
     disponibilités
    -0.47
    havn
    -0.46
    DAYS
    -0.45
    ographiques
    -0.45
    POSITIVE LOGITS
     NUKAT
    0.69
     attack
    0.66
     defenders
    0.64
     attacking
    0.63
     speed
    0.63
     attacks
    0.62
     offensive
    0.61
    greenrobot
    0.61
     blocking
    0.61
     offense
    0.61
    Activations Density 0.322%

    No Known Activations