© 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. 5-CLT-HP
    7. 92599
    Prev
    Next
    INDEX
    Explanations

    identifying something specific

    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
     للمعارف
    -0.69
    SourceChecksum
    -0.68
    elemField
    -0.63
     and
    -0.56
     JADX
    -0.49
    ̀ng
    -0.47
    glLoadIdentity
    -0.46
    rungsseite
    -0.46
     forze
    -0.46
    oneofs
    -0.45
    POSITIVE LOGITS
     method
    0.67
     løs
    0.62
     approach
    0.62
     course
    0.60
     solution
    0.58
     path
    0.57
     direction
    0.57
    AddTagHelper
    0.57
    ục
    0.56
    ModelAdmin
    0.56
    Activations Density 0.002%

    No Known Activations