© 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. 94095
    Prev
    Next
    INDEX
    Explanations

    methylation

    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
     ujednoznacz
    -0.46
    ValueStyle
    -0.45
    ⓧ
    -0.45
    igshid
    -0.44
    Personendaten
    -0.44
    randomUUID
    -0.44
     demografica
    -0.43
    ello
    -0.43
    jspb
    -0.42
     ne
    -0.41
    POSITIVE LOGITS
    UserScript
    0.65
     Babi
    0.64
    Étape
    0.60
     Indexed
    0.60
     Toch
    0.59
    GEBURTSDATUM
    0.59
     snippetHide
    0.56
     createSprite
    0.56
    dafx
    0.54
    ADIAN
    0.54
    Activations Density 0.002%

    No Known Activations