© 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. 1-CLT-HP
    7. 9045
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
    R
    -0.48
    </em>
    -0.47
    log
    -0.46
    段
    -0.42
    bag
    -0.41
     gempa
    -0.41
    lag
    -0.40
    art
    -0.40
    ön
    -0.40
    ViewImports
    -0.40
    POSITIVE LOGITS
    .³
    0.81
    Παραπομπές
    0.79
    Carcinogenicity
    0.71
    idać
    0.69
     fingernails
    0.68
    }")]
    0.68
    ecute
    0.67
    Према
    0.64
    ujan
    0.64
    iented
    0.64
    Activations Density 0.115%

    No Known Activations