© 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. 8992
    Prev
    Next
    INDEX
    Explanations

    sequences of non-alphanumeric characters and specific formatting in text

    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
    providedIn
    -0.47
     Tole
    -0.46
    PreAuthorize
    -0.45
    __;
    -0.44
    quiel
    -0.44
    AxisAlignment
    -0.43
    ėd
    -0.42
    struzione
    -0.42
    存于互联网档案馆
    -0.42
    +:+
    -0.41
    POSITIVE LOGITS
     виправивши
    0.95
     beginnetje
    0.86
    Personensuche
    0.71
    GEBURTSDATUM
    0.69
    =?";
    0.66
     tartalomajánló
    0.63
    ]!='
    0.61
     '-':
    0.59
    migrationBuilder
    0.58
    LookAnd
    0.58
    Activations Density 0.022%

    No Known Activations