© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93796
    Prev
    Next
    INDEX
    Explanations

    current events

    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
    tagHelperRunner
    -0.80
    '])->
    -0.69
    addCriterion
    -0.68
     виправивши
    -0.66
     combineReducers
    -0.65
    WebControls
    -0.64
     onlyOwner
    -0.64
    BeginInit
    -0.63
    DeleteBehavior
    -0.62
    AddField
    -0.61
    POSITIVE LOGITS
     will
    0.69
    ↵↵
    0.68
     could
    0.65
     is
    0.58
     may
    0.57
     might
    0.56
     has
    0.56
     boasts
    0.55
     grew
    0.54
     would
    0.52
    Activations Density 0.001%

    No Known Activations