© 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. 4437
    Prev
    Next
    INDEX
    Explanations

    computer code/generated text

    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
    UserScript
    -0.88
     saites
    -0.80
     للاسماء
    -0.79
     utafitiHapana
    -0.72
    rungsseite
    -0.71
     Савезне
    -0.71
    \{\\
    -0.71
    />";
    -0.70
     الحره
    -0.69
    abestanden
    -0.69
    POSITIVE LOGITS
    ,
    0.52
     early
    0.43
    glGen
    0.42
    Див
    0.42
    getStatusCode
    0.40
    :
    0.40
     pair
    0.39
    -
    0.39
    Gizmos
    0.36
     hard
    0.35
    Activations Density 0.254%

    No Known Activations