© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43507
    Prev
    Next
    INDEX
    Explanations

    Technical/academic text excerpts

    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
     fourth
    -0.54
    ing
    -0.53
    en
    -0.50
    ज्ञ
    -0.50
    s
    -0.50
     third
    -0.49
    e
    -0.47
     ANTONIO
    -0.45
     body
    -0.44
     significance
    -0.43
    POSITIVE LOGITS
    ⓧ
    0.81
    Hochspringen
    0.80
    ]")]
    0.77
     intptr
    0.75
    nościo
    0.69
    omeness
    0.67
    yaszt
    0.65
    pozdrawiam
    0.64
    -------------</
    0.63
    AsUp
    0.62
    Activations Density 0.175%

    No Known Activations