© 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. 96184
    Prev
    Next
    INDEX
    Explanations

    chemical elements

    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
    orianCalendar
    -0.65
     AssemblyCulture
    -0.56
     gustan
    -0.56
    genossen
    -0.53
     taro
    -0.53
    脚注の使い方
    -0.50
     ſeveral
    -0.50
    ioutil
    -0.50
    ComponentName
    -0.50
     Minangkabau
    -0.50
    POSITIVE LOGITS
     يتيمه
    0.54
    doctype
    0.53
    bium
    0.52
    httphttps
    0.50
    extAlignment
    0.50
    diye
    0.48
    lax
    0.48
    yarnpkg
    0.48
    lides
    0.47
    ApiProperty
    0.46
    Activations Density 0.002%

    No Known Activations