© 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. 9986
    Prev
    Next
    INDEX
    Explanations

    Genesis

    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
    Œuvres
    -0.47
    verwijspagina
    -0.46
     Parcelable
    -0.45
    сюда
    -0.44
    কার
    -0.44
    róleo
    -0.44
     actionMode
    -0.43
    property
    -0.42
    LPG
    -0.41
     Mar
    -0.41
    POSITIVE LOGITS
     Theſe
    0.63
     uſed
    0.59
     ſche
    0.56
     pleaſure
    0.56
    astify
    0.56
     Monfieur
    0.56
     myſelf
    0.56
     uſe
    0.55
    Explicación
    0.55
     fubject
    0.54
    Activations Density 0.006%

    No Known Activations