© 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. 4826
    Prev
    Next
    INDEX
    Explanations

    Technical notation

    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
    förs
    -0.43
    férences
    -0.43
    uth
    -0.42
     sementes
    -0.42
     bezeichneter
    -0.42
     strto
    -0.41
    RU
    -0.40
     Farid
    -0.39
    olz
    -0.38
     point
    -0.38
    POSITIVE LOGITS
    XmlAccessorType
    0.77
    sidemargin
    0.77
    HomeAsUpEnabled
    0.72
    __':
    0.71
    __":
    0.65
    URDAY
    0.64
    DataAnnotations
    0.62
     suyo
    0.61
    __':
    0.60
     ')
    0.60
    Activations Density 0.001%

    No Known Activations