© 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. 5-CLT-HP
    7. 91508
    Prev
    Next
    INDEX
    Explanations

    the

    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
     betweenstory
    -0.54
     OMITTED
    -0.53
    transQ
    -0.52
    θεια
    -0.51
     تعدى
    -0.50
    uoco
    -0.49
    apatilla
    -0.48
    стероид
    -0.47
     clue
    -0.45
     mineures
    -0.44
    POSITIVE LOGITS
     dates
    0.66
     date
    0.65
     number
    0.62
    kháu
    0.60
    esModule
    0.60
     types
    0.56
    CodeAttribute
    0.54
    withIdentifier
    0.54
    VersionUID
    0.52
    هة
    0.52
    Activations Density 0.002%

    No Known Activations