© 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. 2965
    Prev
    Next
    INDEX
    Explanations

    Helper words

    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
    <bos>
    -0.74
    
    -0.54
    focus
    -0.49
    #
    -0.46
     focus
    -0.46
     direct
    -0.45
    Focus
    -0.43
     cum
    -0.43
    backends
    -0.43
     focused
    -0.42
    POSITIVE LOGITS
     eût
    0.69
     réguli
    0.69
     createSlice
    0.67
     complètes
    0.65
     laissant
    0.62
     supérieurs
    0.62
     completos
    0.61
    ContentLoaded
    0.61
    PRNewswire
    0.59
     navideños
    0.58
    Activations Density 0.005%

    No Known Activations