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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74460
    Prev
    Next
    INDEX
    Explanations

    code

    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
     deny
    -1.02
     denial
    -0.96
     Admit
    -0.90
     denying
    -0.89
     denies
    -0.87
     Denial
    -0.86
    denial
    -0.85
    ]--;
    -0.84
    ніципа
    -0.84
     Deny
    -0.84
    POSITIVE LOGITS
     fe
    0.38
    HexString
    0.38
     per
    0.35
     sted
    0.34
     protested
    0.34
    कारी
    0.34
     kró
    0.32
    TagMode
    0.32
     tác
    0.32
     bé
    0.31
    Activations Density 0.002%

    No Known Activations