© 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. 4866
    Prev
    Next
    INDEX
    Explanations

    "let alone" or "much less"

    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
    nor
    -0.60
     nor
    -0.56
     slightest
    -0.41
    ήσει
    -0.40
     aveug
    -0.39
    遑
    -0.39
     mitään
    -0.39
     بلکه
    -0.39
    Nor
    -0.38
     moindre
    -0.38
    POSITIVE LOGITS
    __':
    1.09
    __":
    0.96
    astéroïdes
    0.87
    PerformLayout
    0.85
    GraphicsUnit
    0.85
    awtextra
    0.83
    __':
    0.83
     defaultstate
    0.81
     متعلقه
    0.79
    __":
    0.79
    Activations Density 0.038%

    No Known Activations