© 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. 5-CLT-HP
    7. 5428
    Prev
    Next
    INDEX
    Explanations

    measurements and quantities

    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>
    -0.89
     تانيه
    -0.59
    /*
    -0.48
    /**
    -0.48
     متعلقه
    -0.46
    стоинства
    -0.45
    '
    -0.44
    锈钢
    -0.43
    createTextNode
    -0.43
    XmlAccessorType
    -0.43
    POSITIVE LOGITS
    XmlAccessType
    0.81
    Geplaatst
    0.68
     lenker
    0.59
    FieldBuilder
    0.58
     SEDS
    0.57
     nationaux
    0.56
    ArgsConstructor
    0.56
    ciatore
    0.55
     esboço
    0.55
     traditionnels
    0.55
    Activations Density 0.040%

    No Known Activations