© 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. 92381
    Prev
    Next
    INDEX
    Explanations

    ort

    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
    lia
    -0.64
     sin
    -0.57
     la
    -0.55
    <bos>
    -0.53
     of
    -0.52
     war
    -0.51
    La
    -0.50
     w
    -0.49
     La
    -0.49
    LA
    -0.47
    POSITIVE LOGITS
    AutoresizingMask
    0.81
     AssemblyCompany
    0.80
     itſelf
    0.77
    RenderAtEndOf
    0.76
     myſelf
    0.76
     bershka
    0.74
    erate
    0.72
     Theſe
    0.71
    theless
    0.71
     SqlDbType
    0.71
    Activations Density 0.090%

    No Known Activations