© 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. 13127
    Prev
    Next
    INDEX
    Explanations

    environment

    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
    ConstraintMaker
    -0.89
     ProtoMessage
    -0.68
    webElementXpaths
    -0.68
     Normdatei
    -0.66
    VIAF
    -0.64
    fjspx
    -0.59
     betweenstory
    -0.59
    ulario
    -0.59
     onOptions
    -0.58
     esternos
    -0.57
    POSITIVE LOGITS
     friendly
    0.74
     Friendly
    0.57
     friendliness
    0.55
    friendly
    0.54
     pollution
    0.52
    substack
    0.50
     clearance
    0.50
    ✎
    0.50
     Clearance
    0.49
     conservation
    0.48
    Activations Density 0.008%

    No Known Activations