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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 75276
    Prev
    Next
    INDEX
    Explanations

    research/technical

    np_max-act-logits · 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
    twimg
    -0.67
     actionMode
    -0.62
     getItemId
    -0.57
    StoryboardSegue
    -0.54
    Xna
    -0.54
     Stony
    -0.52
    PyExc
    -0.52
    ChildScrollView
    -0.51
    AccessFile
    -0.50
    )++;
    -0.49
    POSITIVE LOGITS
    spirit
    0.66
     spirit
    0.66
    tagHelperRunner
    0.58
     Det
    0.57
    Det
    0.54
    SourceChecksum
    0.51
    Spirit
    0.50
     det
    0.50
     Brunner
    0.49
     SPIRIT
    0.49
    Activations Density 0.000%

    No Known Activations