© 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. 5-CLT-HP
    4. 2621
    Prev
    Next
    INDEX
    Explanations

    is are

    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
     thought
    -0.75
    thought
    -0.65
     believed
    -0.65
    UrlResolution
    -0.61
    LookAnd
    -0.60
    DebuggerNonUser
    -0.59
     said
    -0.54
    BeginContext
    -0.53
     THOUGHT
    -0.53
     assumed
    -0.53
    POSITIVE LOGITS
     starting
    0.73
     turning
    0.66
     killing
    0.65
    starting
    0.65
     breaking
    0.63
     dissolving
    0.63
     swallowing
    0.61
     giving
    0.60
     splitting
    0.59
     settling
    0.57
    Activations Density 0.006%

    No Known Activations