© 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. 93851
    Prev
    Next
    INDEX
    Explanations

    will

    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
    so
    -0.62
     so
    -0.60
    homonymie
    -0.52
     niin
    -0.52
    MigrationBuilder
    -0.51
     så
    -0.48
    ValueGenerated
    -0.47
     tends
    -0.47
     disambiguazione
    -0.46
    ISPR
    -0.46
    POSITIVE LOGITS
     already
    0.69
    viewDidLoad
    0.63
     PhpStorm
    0.59
    already
    0.59
    rrggbb
    0.58
     sortant
    0.57
    getMenuInflater
    0.57
     BoxFit
    0.55
    initWithFrame
    0.54
     vouloir
    0.53
    Activations Density 0.003%

    No Known Activations