© 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. 25309
    Prev
    Next
    INDEX
    Explanations

    references to caution or warnings regarding safety and potential risks

    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
     Blythe
    -0.71
    řské
    -0.69
     Bir
    -0.68
     Shah
    -0.66
     cel
    -0.65
    }^\
    -0.65
    awtextra
    -0.65
    Eccles
    -0.64
    daille
    -0.64
    ves
    -0.63
    POSITIVE LOGITS
     Cau
    1.30
    Cau
    1.23
     cau
    1.07
    caution
    1.06
     Cauchy
    1.00
     Caucus
    0.99
    cautionary
    0.96
     caution
    0.95
    참고
    0.92
    SuppressLint
    0.91
    Activations Density 0.006%

    No Known Activations