© 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. 93157
    Prev
    Next
    INDEX
    Explanations

    bits/requirements

    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
     piattaforma
    -0.58
    pagni
    -0.49
    pav
    -0.44
    Shutterstock
    -0.44
     tavolo
    -0.44
    líben
    -0.43
    Protos
    -0.43
    coroutine
    -0.43
    فة
    -0.42
    obox
    -0.41
    POSITIVE LOGITS
    IndentedString
    0.84
    Personensuche
    0.73
    enumi
    0.72
     Мексичка
    0.71
    detectChanges
    0.67
    Jeografia
    0.67
    XmlAccessType
    0.66
    contentLoaded
    0.65
    EndGlobalSection
    0.65
    MigrationBuilder
    0.64
    Activations Density 0.004%

    No Known Activations