© 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. 1-CLT-HP
    7. 9540
    Prev
    Next
    INDEX
    Explanations

    rests

    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
     gyhoeddwyd
    -0.80
    GEBURTSDATUM
    -0.55
     Kohl
    -0.53
     Infórmanos
    -0.50
    TagMode
    -0.50
    cairn
    -0.48
    ClientSize
    -0.47
    oa̍t
    -0.47
    GrantedAuthority
    -0.45
    KeySpec
    -0.45
    POSITIVE LOGITS
    ArgsConstructor
    0.59
    penup
    0.57
    rsc
    0.52
     PCV
    0.52
     GetEnumerator
    0.52
    Spoljašnje
    0.52
     arşivlendi
    0.51
     division
    0.50
     NDL
    0.49
    도
    0.49
    Activations Density 0.231%

    No Known Activations