© 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. 94049
    Prev
    Next
    INDEX
    Explanations

    coding snippets

    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
     demais
    -0.47
     alluminio
    -0.46
    ::
    -0.46
    <bos>
    -0.46
     Verhältnisse
    -0.45
     Ewig
    -0.43
     namun
    -0.42
    CaseSensitive
    -0.42
     Particular
    -0.42
     ::
    -0.41
    POSITIVE LOGITS
     lenker
    0.74
    دانشنامهٔ
    0.69
     мәкал
    0.68
    StoryboardSegue
    0.67
    脚注の使い方
    0.66
    +#+
    0.65
     smtplib
    0.65
     &___
    0.64
    期刊论文
    0.60
    Cartney
    0.59
    Activations Density 0.001%

    No Known Activations