© 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. 91791
    Prev
    Next
    INDEX
    Explanations

    code and documentation

    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
    SUD
    -0.51
    rieu
    -0.46
    sbc
    -0.44
    EDEFAULT
    -0.42
    ButterKnife
    -0.41
    slut
    -0.41
    misu
    -0.41
     suv
    -0.41
    representative
    -0.41
     sam
    -0.41
    POSITIVE LOGITS
    RenderAtEndOf
    0.81
    Personendaten
    0.80
    principalColumn
    0.75
     دیکھیے
    0.68
     beginnetje
    0.68
    IUrlHelper
    0.65
     bezeichneter
    0.65
    matchCondition
    0.65
    intios
    0.63
    Personensuche
    0.63
    Activations Density 0.000%

    No Known Activations