© 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. 43080
    Prev
    Next
    INDEX
    Explanations

    investigate

    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
     explore
    -1.14
     Explore
    -0.96
    Explore
    -0.96
     examine
    -0.95
     Examine
    -0.93
     investigate
    -0.90
     exploring
    -0.86
    Examine
    -0.84
    explore
    -0.84
     explores
    -0.82
    POSITIVE LOGITS
     the
    0.76
     how
    0.68
     whether
    0.60
     possible
    0.54
     key
    0.54
     regi
    0.52
     “
    0.51
     unknown
    0.51
     ‘
    0.50
     potential
    0.48
    Activations Density 0.139%

    No Known Activations