© 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. 20-CLT-HP
    7. 76645
    Prev
    Next
    INDEX
    Explanations

    Code and medical applications

    np_max-act-logits · 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
     autorytatywna
    -0.97
    Autoritní
    -0.76
    %)$
    -0.65
     Egon
    -0.65
    ratic
    -0.63
    ^(@)
    -0.62
     ſtate
    -0.59
    DeleteBehavior
    -0.58
     Himo
    -0.57
    >>()
    -0.57
    POSITIVE LOGITS
    testens
    0.49
    getSystemService
    0.45
    ModelSerializer
    0.44
     low
    0.43
     Si
    0.43
    setVerticalGroup
    0.43
    ThroughAttribute
    0.43
     do
    0.42
     tears
    0.41
     Référence
    0.40
    Activations Density 0.002%

    No Known Activations