© 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. 43018
    Prev
    Next
    INDEX
    Explanations

    collections

    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
     means
    -0.95
    means
    -0.83
     Means
    -0.75
     collections
    -0.68
    Means
    -0.65
     MEANS
    -0.65
     Collections
    -0.61
    Collections
    -0.60
     networks
    -0.58
    brates
    -0.56
    POSITIVE LOGITS
    InstanceState
    0.74
    الإنجليزية
    0.68
     ***!
    0.67
    ]")]
    0.66
     appellants
    0.65
     defaultstate
    0.65
    amerikanischer
    0.63
    hedrals
    0.63
     insuffisamment
    0.62
    PROMOTED
    0.62
    Activations Density 0.072%

    No Known Activations