© 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. 94030
    Prev
    Next
    INDEX
    Explanations

    Instead

    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
     primary
    -1.15
    Instead
    -1.05
     instead
    -1.04
    primary
    -1.03
     Instead
    -0.98
    instead
    -0.94
     Primary
    -0.92
    Primary
    -0.91
     PRIMARY
    -0.78
     вместо
    -0.76
    POSITIVE LOGITS
     of
    0.82
    DoubleQuotes
    0.57
    Portale
    0.55
    istocene
    0.55
    liferay
    0.53
    jgl
    0.52
    MessageTagHelper
    0.52
     wireType
    0.51
    BeginContext
    0.51
    tonsoft
    0.50
    Activations Density 0.139%

    No Known Activations