© 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. 97481
    Prev
    Next
    INDEX
    Explanations

    positive descriptors

    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
    Personendaten
    -1.10
    UnusedPrivate
    -1.04
    :✨
    -1.03
    RectangleBorder
    -1.02
    WithIOException
    -1.02
     AssemblyTitle
    -1.02
     transfieras
    -1.02
    DockStyle
    -1.01
     ExecuteAsync
    -1.01
    __':
    -0.99
    POSITIVE LOGITS
    ness
    1.08
    e
    0.96
    en
    0.91
    ing
    0.90
    er
    0.90
    y
    0.89
    ly
    0.85
    ment
    0.83
    n
    0.82
    t
    0.80
    Activations Density 0.033%

    No Known Activations