© 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. 95141
    Prev
    Next
    INDEX
    Explanations

    parts, methods, directions

    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
     gain
    -0.77
     Gain
    -0.66
    gain
    -0.62
     Gains
    -0.61
     gains
    -0.57
    ArrowToggle
    -0.56
     hợp
    -0.55
     useDispatch
    -0.55
    gains
    -0.55
    Portale
    -0.53
    POSITIVE LOGITS
    ########.
    0.70
     iprot
    0.61
    entieth
    0.59
    thâu
    0.55
    BufferException
    0.52
    antiation
    0.50
     NDL
    0.50
    tonode
    0.49
    paddingVertical
    0.48
     pheasant
    0.47
    Activations Density 0.183%

    No Known Activations