© 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. 95252
    Prev
    Next
    INDEX
    Explanations

    listing items

    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
    <eos>
    -0.77
     all
    -0.63
    ↵↵
    -0.62
     Gene
    -0.56
    ↵↵↵↵↵
    -0.56
    }}}}
    -0.55
    "]}
    -0.55
     mergeFrom
    -0.55
    ↵↵↵
    -0.53
    )))))
    -0.53
    POSITIVE LOGITS
    ponses
    0.74
     ISNI
    0.64
    tvguidetime
    0.63
     BorderSide
    0.57
     للمعارف
    0.57
    MockBean
    0.57
     <>",
    0.56
    قایناق‌لار
    0.56
     gql
    0.56
    ărul
    0.56
    Activations Density 0.006%

    No Known Activations