© 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. 1-CLT-HP
    7. 9055
    Prev
    Next
    INDEX
    Explanations

    MC

    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
     يتيمه
    -0.84
    TagMode
    -0.75
    ंदीखरीदारी
    -0.72
    adpleegd
    -0.71
    IntoConstraints
    -0.68
     Roskov
    -0.66
    CONSIN
    -0.61
    énario
    -0.61
    éroport
    -0.60
    umab
    -0.60
    POSITIVE LOGITS
    getOut
    0.51
    ngel
    0.40
    ViewImports
    0.40
    unknownFields
    0.39
     power
    0.39
     duty
    0.39
    ChromeDriver
    0.38
    zieh
    0.37
     obligation
    0.37
     Ak
    0.37
    Activations Density 0.044%

    No Known Activations