© 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. 82
    Prev
    Next
    INDEX
    Explanations

    experience

    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
     оригіналу
    -0.57
    jectile
    -0.54
     Roskov
    -0.54
    ernalia
    -0.53
    ckså
    -0.52
    fficients
    -0.51
    ]--;
    -0.51
     riveted
    -0.50
     gypsum
    -0.50
    Tapped
    -0.49
    POSITIVE LOGITS
    aarrggbb
    0.69
    таратура
    0.50
    AxisAlignment
    0.48
    CGContext
    0.48
    原始内容存档于
    0.47
    WireFormatLite
    0.47
    ंदीखरीदारी
    0.47
    AnchorStyles
    0.47
    IsMutable
    0.46
     kec
    0.45
    Activations Density 0.010%

    No Known Activations