© 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. 1-CLT-HP
    7. 10807
    Prev
    Next
    INDEX
    Explanations

    finding something

    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
     find
    -1.18
    find
    -1.14
     found
    -1.13
     finding
    -1.07
     finds
    -1.03
    finding
    -0.99
    Finding
    -0.95
    Find
    -0.94
     Finding
    -0.91
     menemukan
    -0.91
    POSITIVE LOGITS
     Roskov
    0.79
    SharedDtor
    0.73
    setVerticalGroup
    0.72
     kasarigan
    0.71
     GeoNames
    0.64
    aarrggbb
    0.63
    LLocation
    0.63
     Photocase
    0.61
    FieldDescriptor
    0.61
     '{@
    0.61
    Activations Density 0.057%

    No Known Activations