© 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. 5-CLT-HP
    7. 95161
    Prev
    Next
    INDEX
    Explanations

    Instructions and explanations

    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
     laugh
    -0.59
    )}</
    -0.59
     become
    -0.58
    Bef
    -0.56
     Efq
    -0.55
     see
    -0.55
     Become
    -0.54
     Bef
    -0.54
     {:.
    -0.54
    Become
    -0.53
    POSITIVE LOGITS
    脚注の使い方
    0.69
    клопе
    0.57
     most
    0.57
    ########.
    0.56
    rophes
    0.55
     Commencez
    0.54
     mine
    0.52
    oa̍t
    0.49
    phosa
    0.49
     chaude
    0.49
    Activations Density 0.001%

    No Known Activations