© 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. 14391
    Prev
    Next
    INDEX
    Explanations

    locations and people

    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
    styleable
    -0.57
     Dudley
    -0.55
     AttributeSet
    -0.53
     BoxFit
    -0.52
    出版年
    -0.51
     Lyle
    -0.47
     weevil
    -0.45
    bootstrapcdn
    -0.44
     Cedex
    -0.43
     Lec
    -0.43
    POSITIVE LOGITS
    ThroughAttribute
    0.66
    CORBA
    0.61
     calendriers
    0.60
    oredCriteria
    0.59
    mantel
    0.55
    ఔ
    0.55
    ($__
    0.54
    ciaio
    0.54
     consultato
    0.52
     kasarigan
    0.51
    Activations Density 0.072%

    No Known Activations