© 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. 93300
    Prev
    Next
    INDEX
    Explanations

    Broad text

    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
    djangoproject
    -0.84
    !*\
    -0.69
     ModelExpression
    -0.68
    KEYCODE
    -0.67
    viewDidLoad
    -0.66
    AndEndTag
    -0.66
     AppModule
    -0.64
    fret
    -0.61
    rowser
    -0.61
    OwnProperty
    -0.60
    POSITIVE LOGITS
     ehem
    0.50
    yorsunuz
    0.47
    })));
    0.45
     canaux
    0.44
    ed
    0.44
    бри
    0.44
     suitable
    0.44
    …~
    0.43
     maggiori
    0.43
    我们需要
    0.43
    Activations Density 0.001%

    No Known Activations