© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2489
    Prev
    Next
    INDEX
    Explanations

    ?

    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
     متعلقه
    -0.61
    The
    -0.59
    H
    -0.56
    Se
    -0.54
    E
    -0.53
    A
    -0.53
    St
    -0.52
    Heavy
    -0.52
    Ho
    -0.51
     satunya
    -0.51
    POSITIVE LOGITS
    NewUrlParser
    0.75
    IntoConstraints
    0.70
     HasFactory
    0.64
     impea
    0.63
     nonatomic
    0.63
    typeorm
    0.62
     liberalization
    0.60
     Balik
    0.59
    Viitteet
    0.59
     papyrus
    0.59
    Activations Density 0.052%

    No Known Activations