© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3168
    Prev
    Next
    INDEX
    Explanations

    online reputation

    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
     onItemClick
    -0.52
    Портал
    -0.51
    OpenHelper
    -0.47
    BagLayout
    -0.47
    antlr
    -0.47
    GetEnumerator
    -0.47
    owed
    -0.46
    SourceChecksum
    -0.45
    掾
    -0.45
     getItemId
    -0.44
    POSITIVE LOGITS
     risks
    0.65
     risk
    0.61
    rungsseite
    0.60
    risk
    0.59
    risks
    0.56
     Risks
    0.56
     архивлан
    0.56
    ational
    0.55
     harms
    0.55
     harming
    0.54
    Activations Density 0.000%

    No Known Activations