© 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. 4-CLT-HP
    7. 4322
    Prev
    Next
    INDEX
    Explanations

    gmail

    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
    StoryboardSegue
    -0.59
    oredCriteria
    -0.56
    IUrlHelper
    -0.56
     morti
    -0.54
     seen
    -0.54
     inventory
    -0.54
     Rosales
    -0.54
     nemici
    -0.54
     orphans
    -0.53
     spend
    -0.53
    POSITIVE LOGITS
    "]];
    0.66
     gainera
    0.55
    ")]
    0.54
     Normdatei
    0.53
    }*/
    0.52
    )]
    0.52
    ])):
    0.51
    itol
    0.51
    ']],
    0.51
     Audiodateien
    0.50
    Activations Density 0.008%

    No Known Activations