© 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. 12-RES-MATRYOSHKA-DC
    7. 32309
    Prev
    Next
    INDEX
    Explanations

    specific character names and their interactions in a narrative context

    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
    Демографія
    -0.98
    ſelves
    -0.96
    ReusableCell
    -0.93
    '},
    -0.90
     myſelf
    -0.88
    ſelf
    -0.86
     $_"
    -0.85
    IsMutable
    -0.85
     Мексичка
    -0.84
    ьаж
    -0.84
    POSITIVE LOGITS
     sitten
    0.53
    又有
    0.52
    ↵↵
    0.48
     goes
    0.48
     Then
    0.47
    ↵
    0.46
    ...
    0.46
    用
    0.46
    又
    0.45
     pod
    0.45
    Activations Density 0.250%

    No Known Activations