© 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. 94332
    Prev
    Next
    INDEX
    Explanations

    3D

    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
    "
    -0.45
    isation
    -0.44
    ization
    -0.44
     udaler
    -0.43
    dar
    -0.40
     estimés
    -0.38
    yship
    -0.38
     Bedürfn
    -0.36
    }
    -0.36
    /
    -0.35
    POSITIVE LOGITS
    
    0.84
     ReactDOM
    0.74
    __(/*!
    0.69
     onCancelled
    0.68
    webElementGuid
    0.67
     ſeveral
    0.66
    󠁢
    0.66
     NSCoder
    0.65
    StructEnd
    0.65
     أبريل
    0.64
    Activations Density 0.176%

    No Known Activations