© 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. 950
    Prev
    Next
    INDEX
    Explanations

    that

    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
     a
    -0.57
     as
    -0.48
     an
    -0.47
    viewDidLoad
    -0.47
     significant
    -0.46
     vaste
    -0.46
    reloadData
    -0.46
    IntoConstraints
    -0.46
    saying
    -0.45
     at
    -0.45
    POSITIVE LOGITS
     is
    0.99
    '
    0.82
    ’
    0.80
     are
    0.68
     constitutes
    0.67
     has
    0.66
     makes
    0.66
    setopt
    0.65
     فريبيس
    0.65
     seems
    0.63
    Activations Density 0.001%

    No Known Activations