© 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. 0-CLT-HP
    7. 93907
    Prev
    Next
    INDEX
    Explanations

    Being active or shot

    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
     otomatig
    -0.73
     active
    -0.68
     ACTIVE
    -0.65
    DispatchToProps
    -0.61
     Active
    -0.61
     aktif
    -0.60
    leby
    -0.60
    PERATURE
    -0.60
    activate
    -0.59
     Để
    -0.57
    POSITIVE LOGITS
    <bos>
    0.67
    Personendaten
    0.57
     castelo
    0.54
    MessageOf
    0.52
     AssemblyTitle
    0.50
     ↓,
    0.49
     with
    0.49
     endwhile
    0.47
     conosco
    0.47
     fourrure
    0.46
    Activations Density 0.030%

    No Known Activations