© 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. 42566
    Prev
    Next
    INDEX
    Explanations

    promising

    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
     encouraging
    -1.65
     rewarding
    -1.38
     satisfying
    -1.34
     promising
    -1.33
     striking
    -1.31
     gratifying
    -1.24
     discouraging
    -1.21
     appealing
    -1.16
     pleasing
    -1.16
     reassuring
    -1.16
    POSITIVE LOGITS
     the
    0.63
    ly
    0.57
     Nunn
    0.52
    ckså
    0.51
    WRITER
    0.51
    retweeted
    0.51
    führung
    0.50
    äule
    0.50
    miljø
    0.50
     your
    0.49
    Activations Density 0.035%

    No Known Activations