© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74945
    Prev
    Next
    INDEX
    Explanations

    appeared

    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
    expandindo
    -0.84
    StoryboardSegue
    -0.76
     EClass
    -0.75
     AppComponent
    -0.75
    AutoScaleMode
    -0.73
     utafitiHapana
    -0.73
    RenderAtEndOf
    -0.73
    IContainer
    -0.68
     Emits
    -0.66
    
    -0.66
    POSITIVE LOGITS
     safe
    0.49
     jat
    0.42
     menyel
    0.38
     Safe
    0.35
    arev
    0.35
     li
    0.34
    ASS
    0.34
    Coordonnées
    0.34
    upsi
    0.33
    役
    0.33
    Activations Density 0.000%

    No Known Activations