© 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. 5-CLT-HP
    7. 3210
    Prev
    Next
    INDEX
    Explanations

    code or configuration files

    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
    rungsseite
    -0.70
     industriales
    -0.63
    </tfoot>
    -0.62
    Personendaten
    -0.62
     ligiloj
    -0.62
     kaarangay
    -0.60
    IsMutable
    -0.57
    AndroidJUnit
    -0.57
    UnusedPrivate
    -0.56
     nahilalakip
    -0.56
    POSITIVE LOGITS
    FontOfSize
    0.67
     Virtu
    0.61
    AddHtmlAttribute
    0.53
     use
    0.53
     tradition
    0.51
    usepackage
    0.50
    men
    0.50
    stream
    0.50
    kheim
    0.49
    JsonProperty
    0.47
    Activations Density 0.003%

    No Known Activations