© 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. 92203
    Prev
    Next
    INDEX
    Explanations

    and

    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
    ChildScrollView
    -0.93
    MLLoader
    -0.84
     BorderSide
    -0.81
    DockStyle
    -0.81
    StoryboardSegue
    -0.78
    endphp
    -0.76
    astronomie
    -0.75
    ритори
    -0.74
    fony
    -0.74
    EndGlobalSection
    -0.73
    POSITIVE LOGITS
     indeed
    0.41
    .
    0.40
     Similarly
    0.40
    oo
    0.39
    gin
    0.39
    or
    0.39
     people
    0.38
    even
    0.38
    gh
    0.38
    χρι
    0.38
    Activations Density 0.005%

    No Known Activations