© 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. 13318
    Prev
    Next
    INDEX
    Explanations

    connecting

    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
    ValueGeneration
    -0.67
    SequentialGroup
    -0.65
    GenerationType
    -0.64
    っこう
    -0.63
    клопе
    -0.61
     définiti
    -0.60
     joaat
    -0.60
    󠁢
    -0.59
     onAnimation
    -0.59
    ActiveRecord
    -0.58
    POSITIVE LOGITS
     with
    0.71
     together
    0.62
     us
    0.57
    Попис
    0.55
    ficulty
    0.47
     households
    0.43
    ссора
    0.43
     couples
    0.43
     wild
    0.42
     carers
    0.42
    Activations Density 0.001%

    No Known Activations