Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 208
    Prev
    Next
    INDEX
    Explanations

    fix

    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
    Fixed
    -1.13
    fixed
    -1.11
     Fixed
    -1.10
     fixed
    -1.09
    FIXED
    -1.07
     FIXED
    -0.94
     fixing
    -0.80
     Fixation
    -0.77
     fix
    -0.77
     Fix
    -0.77
    POSITIVE LOGITS
    up
    0.57
     a
    0.48
    oa̍t
    0.48
     size
    0.47
     Size
    0.46
    size
    0.45
     up
    0.45
    tagHelperRunner
    0.43
    Height
    0.42
    Size
    0.41
    Activations Density 0.055%

    No Known Activations