© 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. 41182
    Prev
    Next
    INDEX
    Explanations

    sign

    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
     Sign
    -1.12
     sign
    -1.02
    Sign
    -0.93
     SIGN
    -0.85
    SIGN
    -0.76
    sign
    -0.73
     signo
    -0.71
     signs
    -0.69
     Signs
    -0.65
     SIGNS
    -0.60
    POSITIVE LOGITS
     BoxFit
    0.60
    RenderAtEndOf
    0.60
    addPreferredGap
    0.58
    Ранее
    0.58
     فريبيس
    0.57
     defaultstate
    0.56
     oop
    0.55
    iconque
    0.55
     proprement
    0.54
     Normdatei
    0.54
    Activations Density 0.064%

    No Known Activations