© 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. 95075
    Prev
    Next
    INDEX
    Explanations

    any

    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
     any
    -2.75
    any
    -1.99
    Any
    -1.98
     Any
    -1.88
     cualquier
    -1.85
     qualquer
    -1.81
     ANY
    -1.79
     quaisquer
    -1.64
    任何
    -1.63
     anyone
    -1.59
    POSITIVE LOGITS
     kind
    1.09
     sort
    1.03
     degree
    0.83
    sort
    0.79
     thing
    0.78
     amount
    0.77
    kind
    0.74
     number
    0.74
    thig
    0.73
    ones
    0.71
    Activations Density 0.077%

    No Known Activations