© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1261
    Prev
    Next
    INDEX
    Explanations

    flip

    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
     flipping
    -0.95
     flipped
    -0.82
     nahilalakip
    -0.82
     flips
    -0.77
    fli
    -0.75
    Flip
    -0.74
    Fli
    -0.71
     estimés
    -0.71
    flipped
    -0.71
    flip
    -0.69
    POSITIVE LOGITS
    ing
    0.66
    ed
    0.59
    ging
    0.59
    ness
    0.51
    ged
    0.51
    nement
    0.49
    edf
    0.48
    ding
    0.48
    ING
    0.46
    ętr
    0.46
    Activations Density 0.124%

    No Known Activations