© 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. 6144
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically periods and colons

    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
     still
    -0.46
    ']).
    -0.44
     Still
    -0.43
     ladrillo
    -0.43
     bổ
    -0.42
    '],'
    -0.42
    ')]
    -0.41
     a
    -0.40
    ierto
    -0.40
     personnelles
    -0.40
    POSITIVE LOGITS
    OGND
    1.08
    Personensuche
    0.99
     виправивши
    0.97
     Roskov
    0.93
    +#+#
    0.93
    ValueStyle
    0.92
    MessageOf
    0.92
    PerformLayout
    0.91
     bezeichneter
    0.88
    GEBURTSDATUM
    0.86
    Activations Density 0.161%

    No Known Activations