© 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. 40236
    Prev
    Next
    INDEX
    Explanations

    perpendicular

    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
    :✨
    -0.88
     étoient
    -0.86
    ChildScrollView
    -0.84
    AndEndTag
    -0.81
     avoient
    -0.79
     étoit
    -0.77
     préféré
    -0.77
     souple
    -0.77
     auroit
    -0.77
     houſe
    -0.76
    POSITIVE LOGITS
    s
    0.82
    ly
    0.75
    ized
    0.58
     Hy
    0.56
    ally
    0.53
    sm
    0.53
    ︎
    0.53
    ry
    0.52
    ity
    0.52
    eries
    0.51
    Activations Density 0.155%

    No Known Activations