Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73807
    Prev
    Next
    INDEX
    Explanations

    look

    np_max-act-logits · 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
     jScrollPane
    -0.66
    ButtonModule
    -0.52
    ortive
    -0.50
    KIT
    -0.49
    Jor
    -0.49
    phous
    -0.49
    página
    -0.47
     KIT
    -0.47
    TableId
    -0.46
    .*")]
    -0.46
    POSITIVE LOGITS
    __((
    0.74
     Roskov
    0.65
    enumi
    0.65
     незавершена
    0.62
    principalColumn
    0.55
    charpe
    0.55
     فريبيس
    0.54
     their
    0.53
     its
    0.52
    хьтан
    0.51
    Activations Density 0.001%

    No Known Activations