© 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. 4-CLT-HP
    7. 4309
    Prev
    Next
    INDEX
    Explanations

    countries

    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
     U
    -0.81
     E
    -0.53
    atory
    -0.53
    arraycopy
    -0.51
     C
    -0.49
     M
    -0.49
     L
    -0.48
     New
    -0.47
     B
    -0.47
     N
    -0.47
    POSITIVE LOGITS
     estekak
    0.87
    XmlAccessType
    0.85
    bewerken
    0.82
    aarrggbb
    0.75
    tvguidetime
    0.70
     المعيارى
    0.68
    IUrlHelper
    0.66
     vectorielle
    0.64
    IntoConstraints
    0.64
     lumineuse
    0.63
    Activations Density 0.006%

    No Known Activations