© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 545
    Prev
    Next
    INDEX
    Explanations

    levels or scales

    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
     level
    -0.66
    level
    -0.65
     of
    -0.61
    BASEPATH
    -0.57
    or
    -0.56
     LEVEL
    -0.55
    Level
    -0.55
     Level
    -0.54
    Према
    -0.54
    stdc
    -0.49
    POSITIVE LOGITS
     myſelf
    0.83
     Anſ
    0.77
     themſelves
    0.76
     itſelf
    0.76
     ainfi
    0.75
     preſent
    0.75
     ſind
    0.74
     poffible
    0.74
     Monfieur
    0.73
    ſelf
    0.72
    Activations Density 0.095%

    No Known Activations