© 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. 13058
    Prev
    Next
    INDEX
    Explanations

    Web development/documentation

    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
     ComVisible
    -0.56
    исленность
    -0.51
    mål
    -0.50
    batterie
    -0.48
    IVEREF
    -0.47
    DOM
    -0.47
     ChromeDriver
    -0.47
    blos
    -0.46
     batterie
    -0.46
     Batterie
    -0.46
    POSITIVE LOGITS
    ::::::::
    0.59
    __':
    0.57
     nakalista
    0.56
    __':
    0.55
    WriteBarrier
    0.55
    })();
    0.53
    ("'"
    0.52
     ExecuteAsync
    0.51
    __":
    0.50
    openConnection
    0.50
    Activations Density 0.046%

    No Known Activations