© 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. 94859
    Prev
    Next
    INDEX
    Explanations

    discovered/invented

    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
     discovered
    -2.16
    discovered
    -1.96
     Discovered
    -1.87
     invented
    -1.73
     discovers
    -1.28
     detected
    -1.27
     découver
    -1.22
     découvert
    -1.21
     descubierto
    -1.19
     discovering
    -1.17
    POSITIVE LOGITS
     a
    0.63
     the
    0.59
     and
    0.53
     what
    0.50
     an
    0.49
    aVar
    0.48
     some
    0.48
    iprot
    0.47
     something
    0.46
     this
    0.45
    Activations Density 0.391%

    No Known Activations