© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2872
    Prev
    Next
    INDEX
    Explanations

    time

    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
    APTER
    -0.64
    IsContent
    -0.62
     regra
    -0.57
    nitus
    -0.56
    ốt
    -0.56
    bootstrapcdn
    -0.54
    ETHOD
    -0.53
    apter
    -0.53
    pav
    -0.52
    Gatt
    -0.52
    POSITIVE LOGITS
     and
    0.75
     estekak
    0.57
    WebElementEntity
    0.52
     so
    0.50
    OnInit
    0.50
    .
    0.49
     snippetHide
    0.47
     дописавши
    0.46
    ectoria
    0.45
    Nuorodos
    0.45
    Activations Density 0.002%

    No Known Activations