© 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. 4587
    Prev
    Next
    INDEX
    Explanations

    programming

    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
    saraba
    -0.87
     MessageBoxIcon
    -0.79
    IsMutable
    -0.72
    SharedCtor
    -0.66
    Portale
    -0.65
    \{\\
    -0.65
    RegistryLite
    -0.64
     crochê
    -0.61
    intios
    -0.61
    KURZBESCHREIBUNG
    -0.61
    POSITIVE LOGITS
     about
    0.42
    skjaer
    0.39
     Investments
    0.39
     Guzmán
    0.38
    liothèque
    0.38
     Địa
    0.38
     layers
    0.38
    polation
    0.38
    ủy
    0.38
     UFC
    0.37
    Activations Density 0.000%

    No Known Activations