© 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. 1-CLT-HP
    7. 10785
    Prev
    Next
    INDEX
    Explanations

    heat

    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
    -0.70
     SwitchCompat
    -0.57
     <>",
    -0.55
     vPvB
    -0.55
    StringCopy
    -0.54
    ❋
    -0.54
    TargetException
    -0.54
    arakhand
    -0.54
     viewDidLoad
    -0.54
    出版年
    -0.54
    POSITIVE LOGITS
    tispiece
    0.48
    حوالہ
    0.48
    siu
    0.47
    mith
    0.43
    ivi
    0.42
    Inside
    0.42
    oti
    0.41
     ihop
    0.41
    ToBounds
    0.41
    olor
    0.41
    Activations Density 0.002%

    No Known Activations