© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 98296
    Prev
    Next
    INDEX
    Explanations

    others

    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
    endpush
    -0.63
    outros
    -0.63
    ]=="
    -0.62
     springfox
    -0.61
     auroit
    -0.60
     endforeach
    -0.59
     étoient
    -0.59
    ]=>
    -0.59
     ainfi
    -0.57
    POSITIVE LOGITS
    ¿
    0.52
    ardio
    0.50
     spaces
    0.48
     spelling
    0.46
    (…)
    0.45
     Paglinawan
    0.45
    '
    0.44
    ลอง
    0.43
    ’
    0.43
     right
    0.43
    Activations Density 0.003%

    No Known Activations