© 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. 26621
    Prev
    Next
    INDEX
    Explanations

    numeric values with associated standard deviations

    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
    动
    -0.63
     assi
    -0.60
     Nathalie
    -0.59
     Thelma
    -0.59
    -
    -0.59
    be
    -0.56
     Herz
    -0.54
    خی
    -0.54
    Latest
    -0.53
    TO
    -0.52
    POSITIVE LOGITS
    __':
    0.96
     كومونز
    0.96
    MLLoader
    0.92
    __":
    0.90
     vectorielle
    0.88
    etheless
    0.86
    UpInside
    0.85
     contextLoads
    0.84
    getColumnIndex
    0.82
     mourut
    0.81
    Activations Density 0.005%

    No Known Activations