© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13112
    Prev
    Next
    INDEX
    Explanations

    Legal documents

    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
    tvguidetime
    -1.02
    ]-'
    -0.75
    ⓧ
    -0.71
     تضيفلها
    -0.70
    ]='\
    -0.67
    Personendaten
    -0.67
    #+#
    -0.67
     незавершена
    -0.66
     BrowserModule
    -0.66
    rungsseite
    -0.66
    POSITIVE LOGITS
    日閲覧
    0.59
    '
    0.57
    med
    0.57
    ning
    0.57
    ’
    0.52
    nt
    0.50
    ned
    0.49
     mor
    0.48
    СТЬ
    0.48
    InnerText
    0.46
    Activations Density 0.014%

    No Known Activations