© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94744
    Prev
    Next
    INDEX
    Explanations

    seeker

    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
     seek
    -1.05
    seek
    -1.02
     Seek
    -0.98
    seeker
    -0.96
     seeker
    -0.95
    seekers
    -0.91
     SEEK
    -0.85
    Seek
    -0.85
     Seeker
    -0.79
    SEEK
    -0.78
    POSITIVE LOGITS
     Offisielt
    0.71
     Jefus
    0.69
     myſelf
    0.66
     muſt
    0.66
     ſche
    0.65
     EconPapers
    0.64
     Baillargeon
    0.63
     Efq
    0.63
     nahilalakip
    0.63
     whoſe
    0.62
    Activations Density 0.134%

    No Known Activations