© 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. 39895
    Prev
    Next
    INDEX
    Explanations

    ability

    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
    ability
    -2.06
     ability
    -1.73
    Ability
    -1.41
    ABILITY
    -1.36
     Ability
    -1.21
    bility
    -1.09
    tability
    -1.01
     Fähigkeit
    -0.79
    hability
    -0.76
     inability
    -0.75
    POSITIVE LOGITS
    enumi
    0.72
    UnusedPrivate
    0.69
     Computation
    0.67
    ENOMEM
    0.67
    ethene
    0.66
     desorption
    0.66
     CGRect
    0.62
     tearDown
    0.62
     ISNI
    0.62
     titer
    0.60
    Activations Density 0.303%

    No Known Activations