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. 74332
    Prev
    Next
    INDEX
    Explanations

    random text

    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
    ⓧ
    -0.68
     ویکی‌پدیای
    -0.64
    InjectMocks
    -0.58
    дри
    -0.56
    lántico
    -0.54
     SDN
    -0.53
     surla
    -0.52
     Савезне
    -0.50
    rungsseite
    -0.50
    FormTagHelper
    -0.50
    POSITIVE LOGITS
    stylers
    0.47
    ấc
    0.45
     تضيفلها
    0.45
    step
    0.45
    izop
    0.45
    rowse
    0.44
    EndInit
    0.44
    เข้า
    0.43
    iose
    0.43
    CreateIndex
    0.42
    Activations Density 0.000%

    No Known Activations