© 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. 9729
    Prev
    Next
    INDEX
    Explanations

    code

    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
    RTSN
    -0.42
     and
    -0.41
     so
    -0.40
     especiais
    -0.38
    oughlin
    -0.37
    once
    -0.37
    gráfica
    -0.37
    ulemon
    -0.37
    getInputStream
    -0.37
     كذلك
    -0.37
    POSITIVE LOGITS
    PasswordEncoder
    0.84
     BoxFit
    0.81
    tagHelperRunner
    0.79
    FailureListener
    0.79
     समीक्षक
    0.77
     ?>/
    0.77
    Geplaatst
    0.76
    parsedMessage
    0.76
    abestanden
    0.75
     AssemblyCulture
    0.75
    Activations Density 4.847%

    No Known Activations