© 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. 43319
    Prev
    Next
    INDEX
    Explanations

    GH

    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
     ~
    -0.63
     $.
    -0.59
    GH
    -0.55
     []:
    -0.54
     _
    -0.54
     inter
    -0.52
     @
    -0.52
     $-
    -0.50
    MDC
    -0.50
    WebElementEntity
    -0.50
    POSITIVE LOGITS
     avoient
    0.69
     colorés
    0.68
     contextLoads
    0.66
     fermés
    0.66
     Monfieur
    0.66
    Öffnungszeiten
    0.65
    JspWriter
    0.65
     enfans
    0.64
    seamnă
    0.64
     complètes
    0.63
    Activations Density 0.616%

    No Known Activations