© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 495
    Prev
    Next
    INDEX
    Explanations

    the, for

    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
    glGen
    -0.46
    __":
    -0.45
    InputTagHelper
    -0.44
     Mau
    -0.44
     beginnetje
    -0.43
    ])[
    -0.42
    Mau
    -0.42
    crollView
    -0.41
    AutoresizingMask
    -0.40
    NetworkInfo
    -0.40
    POSITIVE LOGITS
     presence
    0.92
     <>",
    0.82
     existence
    0.75
     présence
    0.74
     comuniques
    0.71
    existence
    0.68
    presence
    0.66
     kasarigan
    0.65
     isSet
    0.64
    ercicio
    0.61
    Activations Density 0.002%

    No Known Activations