© 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. 8977
    Prev
    Next
    INDEX
    Explanations

    references to "content" in various contexts

    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
    indd
    -0.66
     doInBackground
    -0.65
     fevere
    -0.61
    pointments
    -0.60
    uterte
    -0.60
    Diwedd
    -0.58
    Esprit
    -0.57
     Zij
    -0.56
     Lombard
    -0.56
     consultato
    -0.55
    POSITIVE LOGITS
    脚注の使い方
    0.78
    CWE
    0.68
    ंदीखरीदारी
    0.67
    cknow
    0.61
    rinfo
    0.58
    WireFormatLite
    0.56
    opsida
    0.56
    .}\
    0.55
     CWE
    0.55
    vimento
    0.54
    Activations Density 0.001%

    No Known Activations