© 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. 1-CLT-HP
    7. 11566
    Prev
    Next
    INDEX
    Explanations

    vulnerability/importance

    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
     immunity
    -0.81
     OFDb
    -0.74
     nakalista
    -0.67
     Immunity
    -0.65
    TagMode
    -0.63
     Wayback
    -0.63
    SequentialGroup
    -0.62
    GEBURTSDATUM
    -0.62
    StoreMessageInfo
    -0.62
    Diwedd
    -0.61
    POSITIVE LOGITS
    anmoins
    0.57
     متعلقه
    0.57
     from
    0.53
    ambilan
    0.51
     devoir
    0.51
     htmlFor
    0.50
     parlant
    0.47
    enseignements
    0.46
     Füße
    0.46
     réguli
    0.45
    Activations Density 0.071%

    No Known Activations