© 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. 3507
    Prev
    Next
    INDEX
    Explanations

    consequence

    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
    XmlAccessType
    -0.60
     Drapeau
    -0.59
    labelledby
    -0.56
     gärna
    -0.54
    IonicModule
    -0.48
    netbeans
    -0.47
    ietal
    -0.46
    tése
    -0.46
    berger
    -0.46
    <%@
    -0.46
    POSITIVE LOGITS
    ValueStyle
    0.69
    ToEnd
    0.61
     Aérea
    0.58
    ResumeLayout
    0.55
     GenerationType
    0.54
    ()");
    0.54
     back
    0.54
    bürgermeister
    0.53
     itself
    0.53
    ").
    0.52
    Activations Density 0.045%

    No Known Activations