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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38941
    Prev
    Next
    INDEX
    Explanations

    rights

    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
     rights
    -1.83
     Rights
    -1.63
    rights
    -1.56
    Rights
    -1.50
     RIGHTS
    -1.46
     droits
    -1.12
     derechos
    -1.11
     direitos
    -1.04
     Rechte
    -1.02
     diritti
    -0.98
    POSITIVE LOGITS
    sizeCache
    0.63
    PositiveButton
    0.46
    éndolo
    0.45
    "}";
    0.44
    HasForeignKey
    0.42
    Beijos
    0.41
     PyTuple
    0.40
    Abraços
    0.40
    getLogger
    0.40
    transQ
    0.40
    Activations Density 0.822%

    No Known Activations