© 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. 4-CLT-HP
    7. 3451
    Prev
    Next
    INDEX
    Explanations

    ensi

    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
     متعلقه
    -0.60
     professionali
    -0.51
     vérit
    -0.48
    cstdio
    -0.48
    uyler
    -0.48
    fromnode
    -0.47
    ']
    -0.45
    下载附件
    -0.45
     Chalmers
    -0.45
    })();
    -0.45
    POSITIVE LOGITS
     utafitiHapana
    0.58
     betweenstory
    0.54
    thâu
    0.54
     OFDb
    0.53
     يتيمه
    0.50
     <=",
    0.50
    ViewImports
    0.50
    slip
    0.49
    MigrationBuilder
    0.49
     mime
    0.48
    Activations Density 0.019%

    No Known Activations