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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75777
    Prev
    Next
    INDEX
    Explanations

    code and technical text

    np_max-act-logits · 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
     AssemblyCulture
    -0.77
     resourceCulture
    -0.58
    httphttps
    -0.58
    جوايز
    -0.57
    +#+#
    -0.55
    脚注の使い方
    -0.51
    letoe
    -0.50
    WithMany
    -0.50
    +#+
    -0.48
     transfieras
    -0.48
    POSITIVE LOGITS
    )";
    0.57
     Kill
    0.52
    }]
    0.50
     Merc
    0.50
    Vega
    0.49
     Quig
    0.48
    }],
    0.47
    RunWith
    0.47
     viscous
    0.46
    kaper
    0.46
    Activations Density 0.001%

    No Known Activations