© 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. 15691
    Prev
    Next
    INDEX
    Explanations

    shrine

    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
    }")]
    -0.69
    ]")]
    -0.68
    createStatement
    -0.60
     GenerationType
    -0.59
     médicaux
    -0.57
     dieux
    -0.57
     enfans
    -0.56
     supérieures
    -0.56
     ***!
    -0.56
     väli
    -0.55
    POSITIVE LOGITS
     Gallo
    0.53
    GetAxis
    0.52
    nasse
    0.51
    openzeppelin
    0.51
    DockStyle
    0.50
     disambiguazione
    0.49
    ρός
    0.49
     utafitiHapana
    0.48
     gallo
    0.48
     canons
    0.47
    Activations Density 0.133%

    No Known Activations