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. 0-CLT-HP
    4. 40915
    Prev
    Next
    INDEX
    Explanations

    social issues

    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
    ing
    -0.78
    er
    -0.74
    issauga
    -0.67
     Vulnerable
    -0.67
    s
    -0.66
    y
    -0.65
    ed
    -0.65
     vulnerable
    -0.63
    ses
    -0.58
    matchCondition
    -0.57
    POSITIVE LOGITS
    }$​
    0.68
    KommentareTeilen
    0.67
     }}(\
    0.54
    MigrationBuilder
    0.52
    '}>
    0.51
    ilibrium
    0.51
    }]
    
    0.51
     bodies
    0.50
    MAV
    0.49
    tizia
    0.49
    Activations Density 0.108%

    No Known Activations