© 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. 4511
    Prev
    Next
    INDEX
    Explanations

    Statements

    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
     are
    -0.91
    httphttps
    -0.82
     Paglinawan
    -0.73
    Vidite
    -0.72
    RegistryLite
    -0.71
    protoimpl
    -0.70
     ourselves
    -0.68
    ValueStyle
    -0.66
    <bos>
    -0.66
    ModelAdmin
    -0.64
    POSITIVE LOGITS
    initComponents
    0.52
    mune
    0.48
    arraycopy
    0.47
     peers
    0.45
     Antioch
    0.45
     pyplot
    0.44
     rabbi
    0.44
    ยาย
    0.44
     migrants
    0.43
    requireNonNull
    0.43
    Activations Density 0.002%

    No Known Activations