© 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. 97645
    Prev
    Next
    INDEX
    Explanations

    ferroelectric

    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
    aryen
    -0.65
     Mandatory
    -0.58
     ducts
    -0.56
     Pende
    -0.55
     Gend
    -0.55
    ̍
    -0.54
    ansen
    -0.53
    vernment
    -0.51
     Pastoral
    -0.51
    granate
    -0.49
    POSITIVE LOGITS
    PerformLayout
    0.67
    onAttach
    0.66
    Lähteet
    0.64
    Skills
    0.53
    skills
    0.53
    pravy
    0.52
     EconPapers
    0.51
     skills
    0.49
    endregion
    0.49
    _/
    0.47
    Activations Density 0.075%

    No Known Activations