© 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. 5655
    Prev
    Next
    INDEX
    Explanations

    Tel

    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
    gonic
    -0.57
    DeleteBehavior
    -0.57
    MemoryWarning
    -0.56
    ंदीखरीदारी
    -0.54
    Зноскі
    -0.50
    jooq
    -0.49
     MotionEvent
    -0.48
    imentel
    -0.48
    geable
    -0.48
     corso
    -0.48
    POSITIVE LOGITS
    .
    0.59
    ./
    0.51
    vox
    0.49
    AFX
    0.48
     încă
    0.48
    tagHelperRunner
    0.48
    CrossRef
    0.47
    nonatomic
    0.46
    . 
    0.46
    rašymas
    0.45
    Activations Density 0.000%

    No Known Activations