© 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. 5-CLT-HP
    7. 3412
    Prev
    Next
    INDEX
    Explanations

    formal

    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
    verwijspagina
    -0.69
    PreferredItem
    -0.66
    orteur
    -0.66
    PyExc
    -0.66
    LookAnd
    -0.66
    __":
    -0.66
    NUMX
    -0.65
     bezeichneter
    -0.65
    )];
    -0.65
    новниш
    -0.65
    POSITIVE LOGITS
    раз
    0.48
    exp
    0.46
     conna
    0.46
    eria
    0.45
    volving
    0.44
    QWidget
    0.43
    atura
    0.43
     besonderer
    0.43
     kov
    0.43
    ry
    0.42
    Activations Density 0.499%

    No Known Activations