© 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. 95135
    Prev
    Next
    INDEX
    Explanations

    software development

    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
    fjord
    -0.48
     for
    -0.47
    udnio
    -0.46
    CHRE
    -0.45
     expect
    -0.45
    ynie
    -0.44
     springfox
    -0.44
    mutlich
    -0.43
     idén
    -0.42
    UserScript
    -0.42
    POSITIVE LOGITS
    脚注の使い方
    0.81
     autorytatywna
    0.79
    例句
    0.65
    AnchorStyles
    0.61
     initComponents
    0.60
    مصادر
    0.59
    fromnode
    0.55
    GOTREF
    0.55
    Lähteet
    0.54
    tvguidetime
    0.53
    Activations Density 0.050%

    No Known Activations