© 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. 91611
    Prev
    Next
    INDEX
    Explanations

    web content snippets

    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
    XmlAccessType
    -0.85
    routeProvider
    -0.56
    acterial
    -0.56
    inage
    -0.53
    alous
    -0.52
    Muz
    -0.52
    esía
    -0.52
    GraphicsUnit
    -0.51
    RuleContext
    -0.51
    ThroughAttribute
    -0.50
    POSITIVE LOGITS
    ImageContext
    0.58
     Privacidade
    0.52
    usercontent
    0.50
     الاطلاع
    0.48
     Wiltshire
    0.48
    Filmografie
    0.47
    yntaxException
    0.46
     Interactive
    0.44
     prodi
    0.44
    tic
    0.44
    Activations Density 0.023%

    No Known Activations