© 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. 98254
    Prev
    Next
    INDEX
    Explanations

    articles

    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
     each
    -0.46
     ;
    -0.43
    ;
    -0.41
    Each
    -0.36
    NSNumber
    -0.35
    FirstResponder
    -0.35
    elé
    -0.35
    inu
    -0.34
     libres
    -0.34
     EACH
    -0.34
    POSITIVE LOGITS
    Personendaten
    0.98
     betweenstory
    0.97
    RenderAtEndOf
    0.88
    DockStyle
    0.87
    تقاوى
    0.86
     '\\;'
    0.86
     myſelf
    0.84
     poffible
    0.84
    AnchorStyles
    0.82
     BoxFit
    0.82
    Activations Density 0.001%

    No Known Activations