© 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. 3901
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    SOUNDBITE
    -0.79
    ніципа
    -0.67
    SPATH
    -0.64
    ConstraintMaker
    -0.63
    出版年
    -0.61
    ScopeManager
    -0.61
     EconPapers
    -0.60
    RepeatedField
    -0.60
     թվական
    -0.59
    ReusableCell
    -0.58
    POSITIVE LOGITS
    @
    0.77
    (
    0.62
     tendances
    0.60
     alluminio
    0.60
     avoient
    0.59
     élevées
    0.59
     affitto
    0.58
    A
    0.57
     étoit
    0.57
     enfans
    0.56
    Activations Density 0.001%

    No Known Activations