© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 95206
    Prev
    Next
    INDEX
    Explanations

    out

    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
     mourut
    -0.76
    ()");
    -0.65
    gatsby
    -0.64
     */;
    -0.63
     étoit
    -0.62
    `;
    
    -0.61
    __':
    
    -0.60
    ?";
    -0.59
     CreateTagHelper
    -0.59
    >`;
    -0.58
    POSITIVE LOGITS
     there
    0.61
     يتيمه
    0.48
     raising
    0.46
     inventing
    0.44
     battling
    0.42
     defeating
    0.41
     PLAYING
    0.41
     robbing
    0.41
     設計
    0.41
     jour
    0.41
    Activations Density 0.002%

    No Known Activations