© 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. 0-CLT-HP
    7. 43348
    Prev
    Next
    INDEX
    Explanations

    admis

    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
    __':
    -0.78
    })`
    -0.54
    __":
    -0.54
    Demografie
    -0.53
     pitää
    -0.52
     flesta
    -0.51
    popd
    -0.50
     joindre
    -0.50
     noodzake
    -0.50
    bedrijf
    -0.49
    POSITIVE LOGITS
     <=",
    0.66
    findpost
    0.64
    LookAnd
    0.63
    setVerticalGroup
    0.62
     EconPapers
    0.60
     ProtoMessage
    0.59
    BagLayout
    0.59
     ErrIntOverflow
    0.58
    IUrlHelper
    0.58
    SourceChecksum
    0.56
    Activations Density 1.247%

    No Known Activations