© 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. 9911
    Prev
    Next
    INDEX
    Explanations

    joining/belonging

    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
     čierna
    -0.64
     étoient
    -0.58
     noires
    -0.57
     chré
    -0.57
     fumée
    -0.55
     čier
    -0.55
     vandens
    -0.55
     skydd
    -0.54
     küpe
    -0.54
     gången
    -0.53
    POSITIVE LOGITS
     hands
    0.77
     hand
    0.74
    iecie
    0.53
     Hands
    0.52
     flag
    0.52
     in
    0.51
     any
    0.49
    PhysRevLett
    0.48
     Hand
    0.48
    hand
    0.47
    Activations Density 0.014%

    No Known Activations