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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 95037
    Prev
    Next
    INDEX
    Explanations

    redirects

    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
    setdefault
    -0.44
     Impact
    -0.43
     HttpStatusCode
    -0.42
    Rhestr
    -0.42
    édric
    -0.40
     gezet
    -0.39
    cadilly
    -0.39
     onAnimation
    -0.38
    Impact
    -0.38
     Geduld
    -0.37
    POSITIVE LOGITS
    MLLoader
    0.93
    IntoConstraints
    0.74
    出版年
    0.70
    InitVars
    0.66
    ilirsiniz
    0.63
     Elvira
    0.62
    XmlAttribute
    0.60
     autorytatywna
    0.60
    Hentet
    0.60
    BufferException
    0.59
    Activations Density 0.003%

    No Known Activations