© 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. 97143
    Prev
    Next
    INDEX
    Explanations

    recognition and establishment

    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
    recognized
    -0.78
    founders
    -0.75
    grandfather
    -0.72
     connus
    -0.70
    committees
    -0.70
    $_['
    -0.66
    grandchildren
    -0.66
    renowned
    -0.66
    reducing
    -0.65
    autant
    -0.64
    POSITIVE LOGITS
    theless
    0.86
    teen
    0.84
    ſelf
    0.83
     raiſ
    0.82
    selves
    0.81
    ſelves
    0.79
     myſelf
    0.76
    neath
    0.75
     uſe
    0.75
     pleaſure
    0.75
    Activations Density 1.029%

    No Known Activations