© 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. 1-CLT-HP
    7. 14462
    Prev
    Next
    INDEX
    Explanations

    of

    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
    FTFY
    -0.59
    InvalidProtocol
    -0.55
     INVENTION
    -0.43
    setGeometry
    -0.42
     findViewById
    -0.41
     kehidupan
    -0.41
    findViewById
    -0.40
     solidari
    -0.40
    ManagedBean
    -0.40
    tott
    -0.40
    POSITIVE LOGITS
    bootstrapcdn
    0.81
    >{@
    0.70
    出版年
    0.68
     myſelf
    0.67
     purpoſe
    0.67
     ſtate
    0.66
    GEBURTS
    0.66
     ſtill
    0.65
     houſe
    0.63
    ſelf
    0.62
    Activations Density 0.007%

    No Known Activations