© 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. 92170
    Prev
    Next
    INDEX
    Explanations

    magnitude

    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
    TestingModule
    -0.97
     autorytatywna
    -0.90
    GEBURTSDATUM
    -0.86
    sidemargin
    -0.77
    hdashline
    -0.77
    Personendaten
    -0.77
    adaptiveStyles
    -0.75
    XMLSchema
    -0.75
    homonymie
    -0.75
    bitField
    -0.74
    POSITIVE LOGITS
     Профиль
    0.47
     afecta
    0.44
     conséquences
    0.44
     consequences
    0.43
    WithEmail
    0.43
     mess
    0.42
     messes
    0.42
     carnage
    0.42
     resultaat
    0.41
     misery
    0.41
    Activations Density 0.005%

    No Known Activations