© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15727
    Prev
    Next
    INDEX
    Explanations

    speed

    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
     enough
    -0.56
     الرياضيه
    -0.56
     فريبيس
    -0.54
    enough
    -0.50
    ENES
    -0.50
    oneofs
    -0.49
     genug
    -0.48
    AddTagHelper
    -0.47
     Wiktionnaire
    -0.46
    രിക്ക
    -0.45
    POSITIVE LOGITS
    ArgsConstructor
    0.63
     bientôt
    0.59
     ActionListener
    0.58
     Alva
    0.58
    >';
    0.58
    __':
    0.57
    __":
    0.56
     Verso
    0.55
    hopefully
    0.55
     Giz
    0.55
    Activations Density 0.110%

    No Known Activations