© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1350
    Prev
    Next
    INDEX
    Explanations

    thousands and numbers

    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
     nakalista
    -0.92
     âgées
    -0.75
     médicaux
    -0.72
     chrétiens
    -0.71
     stället
    -0.71
     igång
    -0.68
     larmes
    -0.67
     épaules
    -0.66
    zelfde
    -0.65
     vectorielles
    -0.65
    POSITIVE LOGITS
    DataAnnotations
    0.64
     parent
    0.56
    hlor
    0.54
    rikes
    0.51
    (!__
    0.51
    sing
    0.50
    nit
    0.50
    s
    0.50
    ôt
    0.50
    brero
    0.49
    Activations Density 0.039%

    No Known Activations