© 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. 1-CLT-HP
    7. 46020
    Prev
    Next
    INDEX
    Explanations

    hey/oh

    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
    ohm
    -1.92
     ohm
    -1.68
     Ohm
    -1.38
    Ohm
    -1.34
     ohms
    -1.01
    providedIn
    -0.73
    MigrationBuilder
    -0.66
     Norvège
    -0.64
    ppur
    -0.59
     HasFactory
    -0.58
    POSITIVE LOGITS
    ific
    0.50
    gent
    0.44
     Gans
    0.43
    ified
    0.43
    pos
    0.42
    StoryboardSegue
    0.42
    InjectAttribute
    0.42
    Geplaatst
    0.41
     FAST
    0.41
    inSlope
    0.41
    Activations Density 0.322%

    No Known Activations