© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 94273
    Prev
    Next
    INDEX
    Explanations

    scientific/medical qualification

    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
    .
    -0.71
    .).
    -0.67
    .
    
    -0.66
    ).
    -0.65
    }$.
    -0.64
    ’.
    -0.63
    }}$.
    -0.63
    ))).
    -0.63
    ”.
    -0.63
    })$.
    -0.62
    POSITIVE LOGITS
    ائص
    0.62
     outright
    0.61
     due
    0.56
     exact
    0.54
     politics
    0.54
    ñores
    0.54
    FunctionFlags
    0.54
    ละเอียด
    0.53
    onActivityResult
    0.53
    PMailer
    0.53
    Activations Density 0.023%

    No Known Activations