© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2078
    Prev
    Next
    INDEX
    Explanations

    house

    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
    <bos>
    -0.85
     againſt
    -0.69
    +#+#
    -0.66
     Externe
    -0.65
     ſta
    -0.65
    rungsseite
    -0.65
     itſelf
    -0.64
     myſelf
    -0.63
     Jefus
    -0.63
     secondaire
    -0.62
    POSITIVE LOGITS
    BoxShadow
    0.56
     typelib
    0.56
     AssemblyCompany
    0.56
    principalTable
    0.55
    MessageState
    0.45
     calculées
    0.43
     viewType
    0.43
    ReusableCell
    0.42
     صوتيه
    0.41
    slidesPer
    0.41
    Activations Density 0.019%

    No Known Activations