© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40705
    Prev
    Next
    INDEX
    Explanations

    discussion site content

    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
    annual
    -0.94
     anuales
    -0.93
    Annual
    -0.88
     annual
    -0.81
     scolaires
    -0.78
     supérieurs
    -0.78
     prochaine
    -0.75
     semplici
    -0.75
     raisonnable
    -0.74
    ReusableCell
    -0.73
    POSITIVE LOGITS
    uxxxx
    0.73
    PreferredItem
    0.64
    <bos>
    0.60
     digit
    0.57
    yx
    0.57
    contentLoaded
    0.57
     mood
    0.56
    VersionUID
    0.55
     Bonita
    0.55
    orcid
    0.55
    Activations Density 0.374%

    No Known Activations