© 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. 20-CLT-HP
    4. 74719
    Prev
    Next
    INDEX
    Explanations

    locations and general information

    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
    GEBURTSDATUM
    -0.77
    FormTagHelper
    -0.77
    StructEnd
    -0.70
     CreateTagHelper
    -0.66
    Abitanti
    -0.61
     تضيفلها
    -0.60
     يلي
    -0.59
     Ayah
    -0.58
    UnknownFieldSet
    -0.58
     estekak
    -0.58
    POSITIVE LOGITS
     uska
    0.45
     raised
    0.43
     Upper
    0.43
    èdia
    0.41
    Upper
    0.41
    dasarkan
    0.40
     OnTrigger
    0.40
    τζ
    0.39
    CON
    0.39
     насељу
    0.39
    Activations Density 0.000%

    No Known Activations