© 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. 5-CLT-HP
    7. 94261
    Prev
    Next
    INDEX
    Explanations

    faces

    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
     mourut
    -0.55
     educativas
    -0.48
     artesanales
    -0.47
     operazioni
    -0.45
     posteriore
    -0.43
     relazioni
    -0.43
    اديم
    -0.43
     únicas
    -0.43
     houve
    -0.42
     voordeel
    -0.42
    POSITIVE LOGITS
     converge
    0.73
     stay
    0.73
     are
    0.71
     alternate
    0.71
     move
    0.69
     radiate
    0.67
    arean
    0.66
     propagate
    0.66
     become
    0.65
     follow
    0.65
    Activations Density 0.000%

    No Known Activations