© 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. 77083
    Prev
    Next
    INDEX
    Explanations

    Technical/code snippets

    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
    QMetaType
    -0.66
    InitVars
    -0.63
     Wiktionnaire
    -0.61
     densité
    -0.60
    fony
    -0.57
    ]))
    -0.57
     виправивши
    -0.57
    Географи
    -0.57
     estekak
    -0.56
     OMITBAD
    -0.56
    POSITIVE LOGITS
    wpi
    0.54
    InstanceState
    0.52
    UserScript
    0.49
    alignSelf
    0.47
     McMahon
    0.46
    rature
    0.44
     NgModule
    0.43
    BuildContext
    0.42
    SqlClient
    0.41
    WebVitals
    0.41
    Activations Density 0.004%

    No Known Activations