© 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. 95169
    Prev
    Next
    INDEX
    Explanations

    room or short

    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
    ställning
    -0.68
     Houſe
    -0.55
     Jefus
    -0.54
     Shakspeare
    -0.52
     houſe
    -0.52
    ology
    -0.51
     Fais
    -0.50
    väg
    -0.49
     ſche
    -0.49
     politiet
    -0.49
    POSITIVE LOGITS
    Geplaatst
    0.72
    addContainerGap
    0.65
    Hentet
    0.60
    StructEnd
    0.60
    ItemBackground
    0.59
    endregion
    0.59
    GetEnumerator
    0.58
     estekak
    0.58
     cherchés
    0.58
    ReusableCell
    0.57
    Activations Density 0.091%

    No Known Activations