© 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. 97767
    Prev
    Next
    INDEX
    Explanations

    >

    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
    ArrowToggle
    -0.72
    UrlResolution
    -0.59
     Waray
    -0.50
    TagMode
    -0.50
    invokeLater
    -0.49
    README
    -0.48
     стъ
    -0.45
    kezett
    -0.45
    ichy
    -0.44
     central
    -0.44
    POSITIVE LOGITS
     it
    0.63
    ,
    0.59
     they
    0.55
    }>;
    0.55
    connects
    0.55
     obstante
    0.54
     but
    0.53
    uttavia
    0.52
     transistors
    0.52
     assists
    0.51
    Activations Density 0.005%

    No Known Activations