© 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. 0-CLT-HP
    7. 93461
    Prev
    Next
    INDEX
    Explanations

    known

    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
     is
    -0.68
     B
    -0.54
     and
    -0.53
    ,
    -0.52
     O
    -0.52
     Ber
    -0.51
     en
    -0.50
     P
    -0.49
     K
    -0.49
     doses
    -0.49
    POSITIVE LOGITS
    ✨:
    0.84
    IntoConstraints
    0.81
     CreateTagHelper
    0.72
     MainAxisSize
    0.67
     étoient
    0.66
    AddHtmlAttribute
    0.66
    addPreferredGap
    0.65
    ✭✭
    0.64
     quæ
    0.64
    astify
    0.63
    Activations Density 0.131%

    No Known Activations