© 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. 1923
    Prev
    Next
    INDEX
    Explanations

    neutral, pausing, scripts

    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
     neutral
    -1.47
    neutral
    -1.34
     Neutral
    -1.27
    Neutral
    -1.19
     neutrality
    -1.08
     neutre
    -0.96
     nation
    -0.91
     neutr
    -0.90
     нейтра
    -0.89
     pause
    -0.88
    POSITIVE LOGITS
     pretence
    0.46
    act
    0.46
    istoitu
    0.46
    (!
    0.45
     bezeichneter
    0.45
     unworthy
    0.44
    element
    0.44
    fjspx
    0.44
     pretreatment
    0.44
    Westfalen
    0.44
    Activations Density 1.533%

    No Known Activations