© 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. 5-CLT-HP
    7. 92017
    Prev
    Next
    INDEX
    Explanations

    code

    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
    RegistryLite
    -0.82
    Portale
    -0.74
    WillAppear
    -0.71
    featureID
    -0.69
    //
    -0.68
    Étymologie
    -0.68
    Lähteet
    -0.68
    ContentAlignment
    -0.67
    oneofs
    -0.67
     ExecuteAsync
    -0.65
    POSITIVE LOGITS
     Cancer
    0.45
    áncer
    0.43
    ansible
    0.40
    kompet
    0.38
     CANCER
    0.38
     Capricorn
    0.38
    rigin
    0.37
    cock
    0.37
     cap
    0.37
     Cap
    0.36
    Activations Density 0.015%

    No Known Activations