© 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. 97976
    Prev
    Next
    INDEX
    Explanations

    databases

    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
     correctes
    -0.67
    GEBURTSDATUM
    -0.66
    RuleContext
    -0.61
    featureID
    -0.57
     invokingState
    -0.55
    tagHelperRunner
    -0.55
    oa̍t
    -0.54
    Diweddarwch
    -0.53
    BeginInit
    -0.51
    aarrggbb
    -0.51
    POSITIVE LOGITS
    DispatchToProps
    0.52
    GoogleApiClient
    0.52
     Obs
    0.50
    TemporalType
    0.50
    TextWatcher
    0.48
     Hoof
    0.48
     (`
    0.47
    estion
    0.47
    фере
    0.47
     Multiple
    0.47
    Activations Density 0.012%

    No Known Activations