© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42186
    Prev
    Next
    INDEX
    Explanations

    elevation

    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
     elevation
    -0.84
     Elevation
    -0.84
    Rising
    -0.84
     Rising
    -0.80
     rising
    -0.75
     elevating
    -0.69
    rising
    -0.69
    Raised
    -0.69
     elevations
    -0.67
     Elevated
    -0.67
    POSITIVE LOGITS
     HasFactory
    0.75
     indisponible
    0.67
     BitmapFactory
    0.66
    InjectAttribute
    0.65
    encore
    0.64
    ographia
    0.63
    ########.
    0.62
     transfieras
    0.62
    edance
    0.62
    SourceChecksum
    0.62
    Activations Density 0.027%

    No Known Activations