© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92516
    Prev
    Next
    INDEX
    Explanations

    and or

    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
    "]}
    -0.54
    \"]
    -0.52
    Predecesor
    -0.51
    Bisous
    -0.50
    bisous
    -0.50
     or
    -0.49
    boten
    -0.49
    xymatrix
    -0.49
    yourself
    -0.48
    })]
    -0.48
    POSITIVE LOGITS
    ImageContext
    0.84
    DoubleQuotes
    0.74
     ModelExpression
    0.73
    ">//
    0.69
    grà
    0.68
    UnknownFieldSet
    0.66
    SequentialGroup
    0.65
    ArgsConstructor
    0.65
    ⓧ
    0.64
    
    0.64
    Activations Density 0.056%

    No Known Activations