Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74441
    Prev
    Next
    INDEX
    Explanations

    Lake

    np_max-act-logits · 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
    ()).
    -0.66
    openConnection
    -0.60
    IntoConstraints
    -0.59
    }).
    -0.59
    ?).
    -0.58
    })).
    -0.58
    );}
    -0.57
    ').
    -0.57
    )".
    -0.56
    ").
    -0.55
    POSITIVE LOGITS
    ParallelGroup
    0.61
    WithMany
    0.53
     Havel
    0.52
     Hut
    0.51
    migrationBuilder
    0.50
    pexpr
    0.50
    binar
    0.50
    ंदीखरीदारी
    0.49
     intptr
    0.47
    ómicos
    0.47
    Activations Density 0.659%

    No Known Activations