© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9271
    Prev
    Next
    INDEX
    Explanations

    blood

    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
    PMailer
    -0.55
     Cap
    -0.51
    يكب
    -0.47
     besta
    -0.44
    enumi
    -0.44
     Shot
    -0.40
     đầy
    -0.40
     Meksiku
    -0.40
    居
    -0.40
     Sur
    -0.39
    POSITIVE LOGITS
    featureID
    0.83
    ंदीखरीदारी
    0.70
     Vikipedi
    0.63
    riae
    0.63
     stanovnika
    0.62
    ترنت
    0.61
    }{*}{}
    0.61
    رشف
    0.61
    WithIOException
    0.61
     paramString
    0.60
    Activations Density 0.089%

    No Known Activations