© 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. 5-CLT-HP
    7. 91357
    Prev
    Next
    INDEX
    Explanations

    but

    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
    complexType
    -0.49
    Him
    -0.45
     milling
    -0.45
     gra
    -0.43
    Erstellt
    -0.42
    ThroughAttribute
    -0.42
    gebob
    -0.42
     lycée
    -0.40
     WERE
    -0.40
    фов
    -0.39
    POSITIVE LOGITS
     he
    0.74
     الحره
    0.59
    GEBURTS
    0.58
     disambiguazione
    0.57
    principalTable
    0.57
    homonymie
    0.57
    Kjelder
    0.57
    timbangkan
    0.56
     giustizia
    0.54
    AndEndTag
    0.54
    Activations Density 0.004%

    No Known Activations