© 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. 5-CLT-HP
    7. 792
    Prev
    Next
    INDEX
    Explanations

    twelve

    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
     spread
    -0.91
     Spread
    -0.89
    spread
    -0.82
    Spread
    -0.82
     poffible
    -0.82
     Spreading
    -0.81
     spreading
    -0.75
     myſelf
    -0.75
    setVerticalGroup
    -0.74
     depositphotos
    -0.73
    POSITIVE LOGITS
     passo
    0.46
    ọi
    0.43
    ʖ
    0.43
    TabIndex
    0.43
    esez
    0.42
    ValueGenerated
    0.42
    まさ
    0.42
    
    0.41
    illir
    0.41
    PDC
    0.41
    Activations Density 0.011%

    No Known Activations