© 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. 1-CLT-HP
    7. 14007
    Prev
    Next
    INDEX
    Explanations

    consequences, effects

    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
    sizeCache
    -0.72
    stantial
    -0.62
     CWE
    -0.60
    TargetException
    -0.57
    InstanceState
    -0.57
    ylase
    -0.57
    principalTable
    -0.57
    KEYCODE
    -0.57
    CppCodeGen
    -0.57
    chach
    -0.54
    POSITIVE LOGITS
    '][]
    0.52
    Theory
    0.50
    ken
    0.48
     Erweiterung
    0.46
     Theory
    0.46
    roe
    0.45
     atencion
    0.45
    ’
    0.45
    าม
    0.44
     officielles
    0.44
    Activations Density 0.004%

    No Known Activations