© 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. 15800
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and references to collaborations or partnerships

    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
    Negative Logits
    WebElementEntity
    -0.77
    RectangleBorder
    -0.73
    endphp
    -0.71
     endregion
    -0.68
    abetes
    -0.68
    NUMX
    -0.68
    Hochspringen
    -0.67
    ]}>
    -0.66
    Clik
    -0.66
    Filmografie
    -0.64
    POSITIVE LOGITS
     Mean
    0.49
    ms
    0.48
     Sweet
    0.45
    Geom
    0.45
     Say
    0.45
     Cope
    0.45
    BitConverter
    0.44
    ApiProperty
    0.44
     Kay
    0.44
     Archer
    0.44
    Activations Density 0.004%

    No Known Activations