© 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. 1-CLT-HP
    7. 10109
    Prev
    Next
    INDEX
    Explanations

    steps instructions

    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
     steps
    -1.47
     step
    -1.32
     Steps
    -1.31
    teps
    -1.30
    steps
    -1.28
    Steps
    -1.24
    step
    -1.20
     STEPS
    -1.20
    STEPS
    -1.15
     Step
    -1.09
    POSITIVE LOGITS
     tri
    0.47
     Tri
    0.46
    ro
    0.45
    持ち
    0.44
    tri
    0.44
    out
    0.43
     to
    0.43
     ro
    0.43
     Tr
    0.42
     much
    0.41
    Activations Density 0.026%

    No Known Activations