© 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. 94377
    Prev
    Next
    INDEX
    Explanations

    ionic

    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
    ionic
    -1.18
     Logical
    -0.83
    Logical
    -0.78
     logical
    -0.71
     chré
    -0.63
     logically
    -0.63
    seamnă
    -0.63
     privées
    -0.61
     religieuses
    -0.60
     Logic
    -0.59
    POSITIVE LOGITS
    hyrchwyd
    0.61
    AndEndTag
    0.61
    UnknownFields
    0.60
     LUMP
    0.57
    devamını
    0.55
    MessageOf
    0.52
    Relacion
    0.50
    Бахар
    0.48
    findpost
    0.48
    gister
    0.47
    Activations Density 1.708%

    No Known Activations