© 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. 93767
    Prev
    Next
    INDEX
    Explanations

    Appellant

    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
    GraphicsUnit
    -0.60
    mappedBy
    -0.47
     minib
    -0.43
    ś
    -0.42
     unsus
    -0.41
     feliz
    -0.41
    UnifiedTopology
    -0.41
    sem
    -0.40
     nar
    -0.39
    andri
    -0.39
    POSITIVE LOGITS
    SourceChecksum
    0.68
     ویکی‌پدیا
    0.65
    ?}",
    0.64
    ỡng
    0.62
     Normdatei
    0.60
     esetben
    0.58
     automatiques
    0.57
    ConstraintMaker
    0.57
     spesa
    0.56
    #+#
    0.56
    Activations Density 0.042%

    No Known Activations