© 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. 5-CLT-HP
    7. 5423
    Prev
    Next
    INDEX
    Explanations

    code and math expressions

    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
    +#+#
    -0.74
     disambiguazione
    -0.61
    UIControlState
    -0.60
     trajets
    -0.60
    expandindo
    -0.58
    abestanden
    -0.57
    ########.
    -0.56
    ThroughAttribute
    -0.52
    :✨
    -0.52
    shall
    -0.52
    POSITIVE LOGITS
    rrggbb
    0.60
     بيها
    0.50
    CodedInputStream
    0.45
     ApiException
    0.45
     proportionately
    0.42
    /*
    0.41
     Normdatei
    0.40
    ConstraintMaker
    0.38
     Estudiantes
    0.38
     InputDecoration
    0.38
    Activations Density 0.010%

    No Known Activations