© 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. 97280
    Prev
    Next
    INDEX
    Explanations

    suggests

    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
    "])
    -0.70
    sugges
    -0.69
    NewLabel
    -0.68
     suggests
    -0.65
    StringTo
    -0.56
    "]];
    -0.56
     Vikipedi
    -0.56
    ]")
    -0.56
    $")
    -0.56
    $"
    -0.55
    POSITIVE LOGITS
     that
    1.09
     they
    0.65
    writeFieldEnd
    0.65
    ว่า
    0.59
    that
    0.59
    SessionFactory
    0.57
    styleUrls
    0.57
    FilterChain
    0.56
    execSQL
    0.54
     kasarigan
    0.53
    Activations Density 0.014%

    No Known Activations