© 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. 18621
    Prev
    Next
    INDEX
    Explanations

    references to quality assessment and metrics related to studies

    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
     morire
    -0.60
    unnitel
    -0.51
     aéreo
    -0.49
     Muc
    -0.49
     morrer
    -0.48
    Autoritní
    -0.48
     mangiare
    -0.47
    tése
    -0.47
     domésticos
    -0.47
    TagMode
    -0.46
    POSITIVE LOGITS
    ]--;
    0.71
     propOrder
    0.66
     שוליים
    0.63
    StoreMessageInfo
    0.62
     كومونز
    0.62
    ,:);
    0.57
    InitVars
    0.57
    "]));
    0.56
    脚注の使い方
    0.55
     án
    0.55
    Activations Density 0.028%

    No Known Activations