© 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. 1636
    Prev
    Next
    INDEX
    Explanations

    flow

    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
     INSEE
    -0.50
     nakalista
    -0.49
    fsp
    -0.48
    hver
    -0.48
    gering
    -0.46
    InvalidProtocol
    -0.46
    ΙΑ
    -0.46
     Qualified
    -0.45
    coming
    -0.45
    เซ
    -0.44
    POSITIVE LOGITS
     freely
    1.12
     smoothly
    0.77
     easily
    0.77
     unchecked
    0.69
     openly
    0.68
     unrestricted
    0.67
     unim
    0.67
     easier
    0.64
     gyhoeddwyd
    0.63
     libremente
    0.62
    Activations Density 0.004%

    No Known Activations