© 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. 5809
    Prev
    Next
    INDEX
    Explanations

    of

    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
     illegally
    -0.44
    oft
    -0.43
     horizontally
    -0.42
     horizontal
    -0.41
     totalt
    -0.41
     обратно
    -0.40
     continuous
    -0.40
    pan
    -0.40
    Pseud
    -0.40
    thaler
    -0.39
    POSITIVE LOGITS
     oprot
    0.84
     للمعارف
    0.82
    __(/*!
    0.79
     CURIAM
    0.71
     itſelf
    0.70
     فريبيس
    0.70
     CreateTagHelper
    0.69
    featureID
    0.69
    󠁢
    0.68
     GenerationType
    0.67
    Activations Density 0.021%

    No Known Activations