© 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. 5-CLT-HP
    7. 2071
    Prev
    Next
    INDEX
    Explanations

    Problems/Issues

    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
     getItemId
    -0.74
    ChildScrollView
    -0.67
     EconPapers
    -0.65
    __":
    -0.65
    __':
    -0.64
    WebpackPlugin
    -0.63
    hetamine
    -0.60
    atnya
    -0.60
    waitKey
    -0.60
    rifuge
    -0.59
    POSITIVE LOGITS
     like
    0.53
    Like
    0.49
     Like
    0.47
    time
    0.46
    četně
    0.45
    like
    0.45
     LIKE
    0.45
    WriteTagHelper
    0.44
     années
    0.43
     słoń
    0.42
    Activations Density 0.008%

    No Known Activations