© 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. 0-CLT-HP
    7. 41991
    Prev
    Next
    INDEX
    Explanations

    Continued

    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
    Continued
    -0.96
    continued
    -0.90
     tartalomajánló
    -0.83
     Continued
    -0.82
     continued
    -0.74
     continuing
    -0.74
     Fair
    -0.69
    apimachinery
    -0.68
    contd
    -0.67
    continuing
    -0.67
    POSITIVE LOGITS
    er
    0.79
     colesterol
    0.63
    o
    0.62
    erate
    0.60
    s
    0.60
     pheasant
    0.59
     Chernobyl
    0.59
    poptosis
    0.59
     defensor
    0.59
    e
    0.57
    Activations Density 0.073%

    No Known Activations