© 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. 5-CLT-HP
    7. 91803
    Prev
    Next
    INDEX
    Explanations

    to

    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
    RectangleBorder
    -0.90
     насељу
    -0.87
    IndentedString
    -0.85
     Réponses
    -0.77
    UnknownFields
    -0.76
    MLLoader
    -0.76
    Portail
    -0.75
     Pingback
    -0.75
     Panels
    -0.74
    .*")]
    -0.74
    POSITIVE LOGITS
     ‘
    0.49
     “
    0.45
     '
    0.43
    ore
    0.43
    ;
    0.42
    ten
    0.42
     ten
    0.41
    :
    0.41
    less
    0.41
     for
    0.40
    Activations Density 0.008%

    No Known Activations