© 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. 95131
    Prev
    Next
    INDEX
    Explanations

    VI

    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
    RegistryLite
    -0.82
     pleaſure
    -0.80
     Anſ
    -0.79
     morphe
    -0.76
     Monfieur
    -0.75
     Diſ
    -0.73
     Theſe
    -0.73
    NameInMap
    -0.71
     purpoſe
    -0.71
     ſeveral
    -0.70
    POSITIVE LOGITS
     He
    0.48
     l
    0.47
    ’
    0.44
     P
    0.44
     I
    0.42
    Véxase
    0.42
     Smith
    0.41
    smooth
    0.41
    '
    0.41
     C
    0.41
    Activations Density 0.054%

    No Known Activations