© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90630
    Prev
    Next
    INDEX
    Explanations

    routes

    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
     portion
    -0.66
     destinées
    -0.66
     Theſe
    -0.65
     routes
    -0.64
     races
    -0.64
     étoient
    -0.64
     avoient
    -0.64
    portion
    -0.63
     ſche
    -0.63
     Houſe
    -0.63
    POSITIVE LOGITS
    matchCondition
    0.62
    thâu
    0.57
    bots
    0.54
    ager
    0.51
    pots
    0.51
    DebuggerNonUser
    0.50
    illaries
    0.50
     StringTokenizer
    0.50
    onsored
    0.49
    iastes
    0.49
    Activations Density 0.101%

    No Known Activations