© 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. 20-CLT-HP
    7. 72619
    Prev
    Next
    INDEX
    Explanations

    Garbled data

    np_max-act-logits · 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
    providedIn
    -0.77
    IUrlHelper
    -0.70
    XmlAccessorType
    -0.69
    setVerticalGroup
    -0.69
    Portail
    -0.69
    KURZBESCHREIBUNG
    -0.67
     &___
    -0.66
    onViewCreated
    -0.66
    HttpPut
    -0.66
    exitRule
    -0.65
    POSITIVE LOGITS
    
    0.54
     soient
    0.51
     once
    0.45
    ]=='
    0.40
     be
    0.40
     z
    0.39
     sélectionnez
    0.39
    '
    0.39
    ==='
    0.38
     scouts
    0.38
    Activations Density 0.001%

    No Known Activations