© 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. 39960
    Prev
    Next
    INDEX
    Explanations

    scientific/medical descriptions

    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
    cessions
    -0.68
    ubblica
    -0.59
     indépendante
    -0.58
     concessions
    -0.55
     concession
    -0.54
    FromArgb
    -0.53
     disponibilités
    -0.53
    onViewCreated
    -0.53
     собой
    -0.51
     físicas
    -0.50
    POSITIVE LOGITS
    клопе
    0.78
    ary
    0.75
    OGND
    0.71
    istic
    0.68
    期刊论文
    0.63
    expandindo
    0.60
    ductory
    0.60
    Brainz
    0.59
    lious
    0.59
    imed
    0.58
    Activations Density 1.747%

    No Known Activations