© 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. 95261
    Prev
    Next
    INDEX
    Explanations

    and

    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
     متعلقه
    -0.72
    Diweddarwch
    -0.62
    ########.
    -0.60
    buie
    -0.56
    جغرافيا
    -0.56
    Portale
    -0.55
    glGet
    -0.53
    رشف
    -0.53
     shipwreck
    -0.53
    ceae
    -0.52
    POSITIVE LOGITS
     suivants
    0.66
     up
    0.58
     suivantes
    0.55
     following
    0.54
     again
    0.52
     above
    0.52
    following
    0.51
     FOLLOWING
    0.49
     seguenti
    0.48
     below
    0.48
    Activations Density 0.016%

    No Known Activations