Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74537
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    <bos>
    -0.30
     e
    -0.18
    ter
    -0.17
     }}"></
    -0.17
    }}}}
    -0.17
     des
    -0.17
    ans
    -0.17
    xe
    -0.16
     van
    -0.16
    bin
    -0.16
    POSITIVE LOGITS
     Theſe
    0.48
     Monfieur
    0.46
     ſeveral
    0.40
     Efq
    0.40
     Económica
    0.39
     myſelf
    0.38
     démocr
    0.38
     becauſe
    0.37
     quæ
    0.37
     scolaires
    0.37
    Activations Density 0.013%

    No Known Activations