© 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. 1-CLT-HP
    7. 352
    Prev
    Next
    INDEX
    Explanations

    movement

    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
    IntoConstraints
    -0.69
     تانيه
    -0.69
     varandra
    -0.65
     continúas
    -0.64
     Normdatei
    -0.63
    movement
    -0.61
    StoryboardSegue
    -0.60
    Parcelize
    -0.60
    thodox
    -0.59
     stället
    -0.59
    POSITIVE LOGITS
     kaarangay
    0.54
     समीक्षाएं
    0.51
    rungsseite
    0.47
    ado
    0.45
    "."
    0.45
    verwijspagina
    0.44
     plan
    0.44
    Välislingid
    0.43
    miso
    0.43
     of
    0.42
    Activations Density 0.015%

    No Known Activations