© 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. 4-CLT-HP
    7. 767
    Prev
    Next
    INDEX
    Explanations

    Modality

    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>
    -0.96
     tartalomajánló
    -0.77
     normaux
    -0.66
     propOrder
    -0.66
     étoit
    -0.64
     colorés
    -0.64
     démocr
    -0.63
    webElementXpaths
    -0.63
     animés
    -0.63
     supérieurs
    -0.62
    POSITIVE LOGITS
     trust
    0.59
    MLLoader
    0.57
    mybatisplus
    0.53
    ThroughAttribute
    0.50
     die
    0.50
     achieve
    0.49
     leave
    0.48
    TintMode
    0.45
     puissiez
    0.45
    makeText
    0.45
    Activations Density 0.017%

    No Known Activations