© 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. 0-CLT-HP
    7. 94407
    Prev
    Next
    INDEX
    Explanations

    suicide

    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
    Conventional
    -1.06
    conventional
    -1.02
     Conventional
    -0.98
     conventional
    -0.96
    :✨
    -0.88
     convention
    -0.85
    Convention
    -0.85
     Convention
    -0.81
    convention
    -0.80
     conventionally
    -0.80
    POSITIVE LOGITS
     on
    0.57
    ắm
    0.51
    ly
    0.47
     band
    0.47
     last
    0.47
     for
    0.45
    LookAnd
    0.45
    PageContext
    0.45
     money
    0.45
    ts
    0.44
    Activations Density 1.939%

    No Known Activations