© 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. 0-CLT-HP
    7. 39809
    Prev
    Next
    INDEX
    Explanations

    proper nouns titles

    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
    cussion
    -0.91
    orin
    -0.87
     Gaines
    -0.81
    }]);
    -0.54
    CUSSION
    -0.48
     bal
    -0.47
     möjligt
    -0.46
     Pauly
    -0.46
    โก
    -0.46
    Dữ
    -0.45
    POSITIVE LOGITS
    期刊论文
    0.75
     utafitiHapana
    0.70
     виправивши
    0.65
     ContentValues
    0.64
    httphttps
    0.64
     '\\;'
    0.64
     CURIAM
    0.62
    tyimages
    0.59
     AssemblyCulture
    0.59
     Numerade
    0.58
    Activations Density 0.531%

    No Known Activations