© 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. 5-CLT-HP
    7. 97831
    Prev
    Next
    INDEX
    Explanations

    -

    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
    setViewportView
    -0.54
     ModelExpression
    -0.54
    følgelig
    -0.45
    */;
    -0.43
    matchCondition
    -0.43
     zewnętrzne
    -0.42
     sebanyak
    -0.41
    »։
    -0.40
    }`}>
    -0.40
     */;
    -0.40
    POSITIVE LOGITS
     Roskov
    0.62
    Rujuakan
    0.58
    Portale
    0.56
    vature
    0.54
    URN
    0.54
    locking
    0.54
    dich
    0.53
     näin
    0.53
    ynchron
    0.53
    textwidth
    0.51
    Activations Density 0.017%

    No Known Activations