© 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. 5029
    Prev
    Next
    INDEX
    Explanations

    multimedia content

    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
    writeField
    -0.66
    dike
    -0.65
    encodeWith
    -0.61
    TagHelper
    -0.60
    pasti
    -0.59
    DispatchToProps
    -0.59
    AutoScaleMode
    -0.57
    places
    -0.57
    참고
    -0.54
     Fut
    -0.54
    POSITIVE LOGITS
    s
    0.68
    GRAPHY
    0.48
     minOccurs
    0.47
    softc
    0.45
    ся
    0.45
     ProtoMessage
    0.44
    Personensuche
    0.44
    Hentet
    0.43
    )_/¯
    0.43
     AND
    0.42
    Activations Density 0.001%

    No Known Activations