© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93704
    Prev
    Next
    INDEX
    Explanations

    powerful

    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
     '\\;'
    -0.66
    verwijspagina
    -0.66
     виправивши
    -0.56
     nakalista
    -0.55
    NgModule
    -0.52
     stories
    -0.52
    SequentialGroup
    -0.50
    çoivent
    -0.50
     resourceCulture
    -0.50
     Hadi
    -0.50
    POSITIVE LOGITS
    Espèce
    0.71
    ScopeManager
    0.66
    transQ
    0.55
    EndTag
    0.55
     if
    0.53
    ValueStyle
    0.52
     JAXBElement
    0.52
     SqlParameter
    0.52
    RTEE
    0.50
    裟
    0.49
    Activations Density 0.000%

    No Known Activations