© 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. 1-CLT-HP
    7. 13040
    Prev
    Next
    INDEX
    Explanations

    succeeded

    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
     succeeded
    -0.84
     Esk
    -0.66
    (!__
    -0.59
    findpost
    -0.58
    expandindo
    -0.58
    getMenuInflater
    -0.57
    WithIOException
    -0.56
    StoreMessageInfo
    -0.56
     "'");
    -0.56
    دانشنامهٔ
    -0.55
    POSITIVE LOGITS
     Catawiki
    0.56
     Gama
    0.51
     ATTR
    0.50
     Loi
    0.50
    ManagedBean
    0.47
     BeautifulSoup
    0.46
     jednak
    0.46
     Adonis
    0.46
    truk
    0.45
     limp
    0.45
    Activations Density 0.236%

    No Known Activations