© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41806
    Prev
    Next
    INDEX
    Explanations

    code

    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
    rrggbb
    -0.83
    SequentialGroup
    -0.75
    ValueStyle
    -0.67
     linkovi
    -0.66
    Craig
    -0.65
    httphttps
    -0.62
    AndEndTag
    -0.61
    tinyos
    -0.60
     Craig
    -0.59
    
    -0.59
    POSITIVE LOGITS
    niów
    0.48
    CONTR
    0.48
    ømme
    0.47
    LAYOUT
    0.47
    getMenuInflater
    0.46
    nict
    0.46
    ત્
    0.45
    账
    0.45
    akos
    0.44
    elts
    0.44
    Activations Density 0.394%

    No Known Activations