© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14234
    Prev
    Next
    INDEX
    Explanations

    expressions of liking or positive sentiment

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Audiodateien
    -0.73
    abestanden
    -0.68
    脚注の使い方
    -0.66
    المناصب
    -0.63
    PreExecute
    -0.60
     riguarda
    -0.59
    <bos>
    -0.57
    \{\\
    -0.56
     spécialement
    -0.55
    Cyfarwyddwr
    -0.55
    POSITIVE LOGITS
     liked
    0.69
     loved
    0.61
     aimez
    0.61
     Loved
    0.60
     liking
    0.59
    loved
    0.59
    achusetts
    0.57
    artamento
    0.57
     favorite
    0.56
     favored
    0.54
    Activations Density 0.007%

    No Known Activations