© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12010
    Prev
    Next
    INDEX
    Explanations

    procedure

    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
    MigrationBuilder
    -0.81
     defaultstate
    -0.71
    StructEnd
    -0.68
     оригіналу
    -0.66
    Personensuche
    -0.64
    __*/
    -0.64
    aimerais
    -0.63
     Paglinawan
    -0.63
    oa̍t
    -0.60
    sizeCache
    -0.58
    POSITIVE LOGITS
    muth
    0.53
    ಳ
    0.52
    tiche
    0.49
     segn
    0.47
    ally
    0.47
     $:$
    0.46
    point
    0.45
    SourceChecksum
    0.45
    >");
    0.44
    سوب
    0.44
    Activations Density 0.005%

    No Known Activations