© 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. 5-CLT-HP
    7. 5463
    Prev
    Next
    INDEX
    Explanations

    diverse quotes and tech

    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
    脚注の使い方
    -0.84
    WithIOException
    -0.84
    Personensuche
    -0.77
    Personendaten
    -0.73
    VersionUID
    -0.73
     defaultstate
    -0.70
     oprot
    -0.70
     AssemblyProduct
    -0.70
    EditorBrowsable
    -0.69
    tagHelperRunner
    -0.67
    POSITIVE LOGITS
     “
    0.52
     he
    0.52
    Mr
    0.43
    Ms
    0.42
    GI
    0.41
    们
    0.41
    他說
    0.41
    vs
    0.41
    He
    0.40
    是他
    0.40
    Activations Density 0.002%

    No Known Activations