© 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. 15346
    Prev
    Next
    INDEX
    Explanations

    references to telephone usage and related requests

    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
    Datuak
    -0.65
    //
    -0.57
    icoot
    -0.56
    colazione
    -0.56
    ządu
    -0.55
     sacro
    -0.52
    </caption>
    -0.52
    shub
    -0.52
     scolaires
    -0.52
     τ
    -0.51
    POSITIVE LOGITS
     callers
    0.94
     telephone
    0.92
     phone
    0.85
     telephones
    0.82
     caller
    0.82
    telephone
    0.79
     telefon
    0.79
     Telephone
    0.77
     telef
    0.76
     voicemail
    0.75
    Activations Density 0.059%

    No Known Activations