© 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. 23838
    Prev
    Next
    INDEX
    Explanations

    names of people, specifically in the context of correspondence or messages

    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
     initComponents
    -0.94
     חיצוניים
    -0.92
    GEBURTSDATUM
    -0.90
     tartalomajánló
    -0.86
     виправивши
    -0.84
     AssemblyVersion
    -0.82
    rungsseite
    -0.82
     للاسماء
    -0.79
    AndEndTag
    -0.79
    cadilly
    -0.78
    POSITIVE LOGITS
    ↵
    0.50
    ↵↵
    0.50
    @
    0.49
    </strong>
    0.47
    ant
    0.44
     @
    0.43
    _
    0.41
    http
    0.40
    if
    0.40
     |
    0.40
    Activations Density 0.015%

    No Known Activations