© 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. 0-CLT-HP
    4. 97730
    Prev
    Next
    INDEX
    Explanations

    below

    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
    Démographie
    -0.76
     Rumania
    -0.68
    __.__
    -0.67
     fibrillation
    -0.66
    Diweddarwch
    -0.66
     mergeFrom
    -0.66
    vantaged
    -0.65
     Byzantium
    -0.65
    expandindo
    -0.64
     PLA
    -0.63
    POSITIVE LOGITS
    <bos>
    0.57
     disponibilités
    0.52
    }());
    0.46
    المناصب
    0.43
    Hozzáférés
    0.43
    ResumeLayout
    0.42
    tagHelper
    0.42
    fycat
    0.42
    ="@+
    0.42
     finito
    0.41
    Activations Density 0.026%

    No Known Activations