© 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. 4-CLT-HP
    7. 3453
    Prev
    Next
    INDEX
    Explanations

    net

    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
    TagHelper
    -0.66
    poco
    -0.45
    Nigerian
    -0.44
     Nigerian
    -0.43
    aryen
    -0.42
    CHIN
    -0.41
    ']>
    -0.41
     to
    -0.41
    Aktuelle
    -0.41
     imperfect
    -0.41
    POSITIVE LOGITS
     виправивши
    0.63
     Мексичка
    0.63
    +#+#
    0.63
    ArrowToggle
    0.62
     doInBackground
    0.59
    WithIOException
    0.59
     дописавши
    0.57
    ridos
    0.56
    phism
    0.56
    ContentAsync
    0.54
    Activations Density 0.016%

    No Known Activations