© 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-CLT-HP
    7. 93049
    Prev
    Next
    INDEX
    Explanations

    averaging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.58
    ación
    -0.49
     WC
    -0.49
    featureID
    -0.49
    WC
    -0.48
    rick
    -0.47
    addCriterion
    -0.46
    saraba
    -0.46
     management
    -0.45
    arden
    -0.44
    POSITIVE LOGITS
    CORBA
    0.60
     Weiterbildung
    0.59
    diocese
    0.59
    litos
    0.58
    crowned
    0.57
    newswire
    0.56
    ssysteme
    0.56
    tocin
    0.55
    MnO
    0.55
    GMENT
    0.54
    Activations Density 0.145%

    No Known Activations