© 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. 438
    Prev
    Next
    INDEX
    Explanations

    Dates and numbers

    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
    <bos>
    -0.63
    fjspx
    -0.57
     cru
    -0.51
     sisters
    -0.48
     judges
    -0.47
     Pharisees
    -0.47
    Cru
    -0.47
     Tuscan
    -0.46
     crucified
    -0.46
     judged
    -0.45
    POSITIVE LOGITS
    tvguidetime
    0.98
     comportements
    0.68
     automatiques
    0.67
    zzleHttp
    0.66
    jgl
    0.66
    +#+
    0.65
    codable
    0.63
     AssemblyCulture
    0.63
    digarh
    0.62
    cesis
    0.60
    Activations Density 0.001%

    No Known Activations