© 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. 20-CLT-HP
    7. 74670
    Prev
    Next
    INDEX
    Explanations

    Technical/Jargon text

    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
    InvalidProtocol
    -0.56
     gynhyrchwyd
    -0.53
    ipts
    -0.52
    yfik
    -0.49
    Noice
    -0.49
    iální
    -0.46
    tgärder
    -0.46
     superposition
    -0.46
    halla
    -0.46
    rungsseite
    -0.45
    POSITIVE LOGITS
    Chham
    0.54
    casian
    0.52
     uitz
    0.52
    StoryboardSegue
    0.50
    ")));
    0.50
    Alike
    0.50
    })*/
    0.50
    UVWXYZ
    0.49
    >//
    0.49
     surla
    0.49
    Activations Density 0.003%

    No Known Activations