© 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. 1-CLT-HP
    7. 14820
    Prev
    Next
    INDEX
    Explanations

    Note/Noted

    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
    NUMX
    -0.64
     myſelf
    -0.60
    hould
    -0.59
    はじめに
    -0.59
    duled
    -0.57
     faſt
    -0.57
     beginnetje
    -0.56
     poffible
    -0.55
    erover
    -0.55
     kaarangay
    -0.55
    POSITIVE LOGITS
     that
    0.73
    .
    0.63
    ,
    0.59
     where
    0.59
     the
    0.57
     something
    0.57
    findpost
    0.56
     there
    0.52
     this
    0.50
     we
    0.50
    Activations Density 1.374%

    No Known Activations