© 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. 94902
    Prev
    Next
    INDEX
    Explanations

    Scientific/formal processes

    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
     morire
    -0.65
     substitute
    -0.61
     accompany
    -0.58
     accompanies
    -0.58
     befall
    -0.58
     employ
    -0.57
     endeavor
    -0.55
    Koordinaten
    -0.54
     Connectez
    -0.54
    はじめに
    -0.53
    POSITIVE LOGITS
    .*")]
    0.63
    InjectMocks
    0.57
    存于互联网档案馆
    0.57
    ✨:
    0.55
    ))){
    0.55
     nakalista
    0.52
    uai
    0.51
    }{*}{
    0.51
    extAlignment
    0.51
    }")]
    0.50
    Activations Density 0.889%

    No Known Activations