© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93175
    Prev
    Next
    INDEX
    Explanations

    fi

    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
    IsContent
    -0.71
    pend
    -0.66
    DeleteBehavior
    -0.65
    ped
    -0.64
     sided
    -0.64
     ped
    -0.63
    رشف
    -0.61
    LookAnd
    -0.60
    ViewFeatures
    -0.60
    MLLoader
    -0.59
    POSITIVE LOGITS
     varandra
    0.65
     zijne
    0.60
     enfans
    0.60
     ویکی‌پدیای
    0.56
     eenige
    0.54
     avoient
    0.54
     feroit
    0.53
    sofa
    0.52
    anglès
    0.51
     étoient
    0.51
    Activations Density 1.168%

    No Known Activations