© 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. 9475
    Prev
    Next
    INDEX
    Explanations

    phone numbers and references to calling for assistance

    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
    atario
    -0.55
    larım
    -0.54
    nościo
    -0.53
    antMatchers
    -0.51
    انتهای
    -0.50
     către
    -0.49
    myModal
    -0.49
    yne
    -0.49
    ceros
    -0.49
    ativement
    -0.49
    POSITIVE LOGITS
     estekak
    0.76
    setVerticalGroup
    0.75
     FetchType
    0.67
     telefónica
    0.63
    LookAnd
    0.62
    awtextra
    0.62
    GraphicsUnit
    0.61
     onCreateView
    0.61
     Anfitrión
    0.61
    bootstrapcdn
    0.60
    Activations Density 0.016%

    No Known Activations