© 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. 1248
    Prev
    Next
    INDEX
    Explanations

    Ful

    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
     volunteered
    -0.75
     volunteering
    -0.70
    LookAnd
    -0.69
    }}$\\
    -0.65
     volunteer
    -0.62
    ]\\
    -0.61
    :]:
    -0.61
     Boulevard
    -0.60
    GEBURTSDATUM
    -0.59
    })));
    -0.59
    POSITIVE LOGITS
    neath
    0.58
    quel
    0.57
    ager
    0.53
    si
    0.52
    st
    0.50
    ns
    0.50
    WebServlet
    0.50
    ization
    0.49
    Referencias
    0.49
    che
    0.48
    Activations Density 0.107%

    No Known Activations