© 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. 5-CLT-HP
    7. 94158
    Prev
    Next
    INDEX
    Explanations

    model

    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
    [-
    -0.42
    per
    -0.41
    .
    -0.41
    PageFactory
    -0.38
    .;
    -0.38
    pa
    -0.38
    aka
    -0.37
    すら
    -0.37
    ;
    -0.37
    Pa
    -0.36
    POSITIVE LOGITS
    <bos>
    1.24
     للمعارف
    1.23
    SourceChecksum
    1.15
     AttributeSet
    1.12
     كومونز
    1.09
    tagHelperRunner
    1.03
    EndGlobalSection
    1.02
     vectorielle
    0.99
    LookAnd
    0.95
    MigrationBuilder
    0.94
    Activations Density 0.002%

    No Known Activations