© 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. 4-CLT-HP
    7. 3086
    Prev
    Next
    INDEX
    Explanations

    code

    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
    WriteBarrier
    -0.54
    MetaObject
    -0.54
    rodu
    -0.53
     Ulm
    -0.52
    HasAnnotation
    -0.52
    ATOM
    -0.52
     Spit
    -0.51
    OSSARY
    -0.50
     memp
    -0.50
     himo
    -0.50
    POSITIVE LOGITS
    Parcelable
    0.54
    nskap
    0.53
     sociales
    0.49
     speranza
    0.49
    iprot
    0.48
     charité
    0.47
    RuleContext
    0.47
    vied
    0.46
    elemField
    0.46
     felicità
    0.46
    Activations Density 0.003%

    No Known Activations