© 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. 20-CLT-HP
    7. 73428
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act-logits · 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
    ReusableCell
    -0.56
    mer
    -0.56
    def
    -0.49
     da
    -0.48
    go
    -0.48
    gor
    -0.48
     Def
    -0.48
    ORT
    -0.48
    arj
    -0.48
     désol
    -0.47
    POSITIVE LOGITS
    yntaxException
    0.72
     '\\;'
    0.70
    
    0.66
     بيها
    0.63
     Infórmanos
    0.63
    ########.
    0.62
    tagHelperRunner
    0.62
    +#+#
    0.60
    oneofs
    0.60
    EClass
    0.59
    Activations Density 0.004%

    No Known Activations