© 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. 42637
    Prev
    Next
    INDEX
    Explanations

    came

    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
    bootstrapcdn
    -0.92
    ImageContext
    -0.90
     itſelf
    -0.86
     cohomology
    -0.85
    Portail
    -0.84
    TypedDataSet
    -0.84
     photolibrary
    -0.82
     doubtnut
    -0.80
     Normdatei
    -0.79
    ValueStyle
    -0.79
    POSITIVE LOGITS
     to
    0.69
     in
    0.64
     as
    0.58
     To
    0.55
    ↵
    0.54
     In
    0.53
     
    0.51
    </em>
    0.50
     T
    0.49
     and
    0.49
    Activations Density 0.028%

    No Known Activations