© 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. 0-CLT-HP
    7. 44178
    Prev
    Next
    INDEX
    Explanations

    roster

    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
     roster
    -1.76
     Roster
    -1.24
    roster
    -1.12
    Roster
    -0.88
     disponibilités
    -0.47
     proposés
    -0.45
     peccato
    -0.44
     riscal
    -0.44
    -};
    -0.43
     proposée
    -0.43
    POSITIVE LOGITS
    ed
    0.73
     jScrollPane
    0.65
     esternos
    0.62
    enumi
    0.60
    HandlerContext
    0.60
    ThroughAttribute
    0.59
     Normdatei
    0.58
    +#+
    0.57
     resourceCulture
    0.57
    🏻
    0.57
    Activations Density 2.235%

    No Known Activations