© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97781
    Prev
    Next
    INDEX
    Explanations

    writing

    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
    rogens
    -0.40
     calendriers
    -0.39
     Pawn
    -0.39
     formats
    -0.39
    CopyWith
    -0.38
     acamp
    -0.37
    Wound
    -0.37
    getOutputStream
    -0.36
     Warming
    -0.36
     Evolve
    -0.36
    POSITIVE LOGITS
     and
    0.76
    esModule
    0.68
     arşivlendi
    0.60
    NUMX
    0.59
    mybatisplus
    0.59
     imageNamed
    0.57
    нию
    0.55
     renseignements
    0.55
    RegistryLite
    0.54
    dataclass
    0.54
    Activations Density 0.000%

    No Known Activations