© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8924
    Prev
    Next
    INDEX
    Explanations

    ophy

    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
    <bos>
    -1.23
    ConstraintMaker
    -0.67
    ScopeManager
    -0.62
    AsUp
    -0.60
     الرياضيه
    -0.59
    MethodManager
    -0.56
     PublicKey
    -0.55
    Chham
    -0.54
    SerializedSize
    -0.52
    tonode
    -0.52
    POSITIVE LOGITS
     Poto
    0.71
    cjs
    0.58
     bunting
    0.57
     Egyptians
    0.56
     Bunting
    0.55
    μαι
    0.54
     Arian
    0.52
    })*/
    0.52
     Persians
    0.52
    });*/
    0.52
    Activations Density 0.106%

    No Known Activations