© 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. 9401
    Prev
    Next
    INDEX
    Explanations

    of

    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
     mesmas
    -0.43
     sorts
    -0.37
    of
    -0.37
     ehem
    -0.36
     allons
    -0.36
     ausger
    -0.36
     course
    -0.36
     primeras
    -0.35
     hijas
    -0.35
    course
    -0.34
    POSITIVE LOGITS
    InvalidProtocol
    1.05
    argout
    0.91
    клопе
    0.91
     Signalez
    0.90
     and
    0.89
    __":
    0.87
    AddTagHelper
    0.85
    bootstrapcdn
    0.84
    __':
    0.83
    </caption>
    0.83
    Activations Density 0.274%

    No Known Activations