© 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. 0-CLT-HP
    7. 95333
    Prev
    Next
    INDEX
    Explanations

    challenge/question

    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
     (
    -0.54
     T
    -0.53
     
    -0.53
     the
    -0.52
    ing
    -0.47
    usepackage
    -0.47
     O
    -0.44
     +
    -0.44
     D
    -0.43
     host
    -0.43
    POSITIVE LOGITS
     juridiques
    0.78
     myſelf
    0.77
     betweenstory
    0.76
     ſind
    0.75
     purpoſe
    0.75
     itſelf
    0.75
    $")
    0.73
    ToScroll
    0.72
     ragaz
    0.71
     doubtnut
    0.71
    Activations Density 0.034%

    No Known Activations