© 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. 11727
    Prev
    Next
    INDEX
    Explanations

    also

    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
    Ещё
    -0.80
    ConstraintMaker
    -0.79
     organisational
    -0.79
    organised
    -0.74
     behavioural
    -0.73
     mobilisation
    -0.73
    behaviour
    -0.73
     organisers
    -0.73
     also
    -0.73
     optimised
    -0.71
    POSITIVE LOGITS
     will
    0.59
     is
    0.57
     are
    0.50
     may
    0.50
     might
    0.49
     was
    0.48
     should
    0.46
     would
    0.44
     must
    0.43
     can
    0.42
    Activations Density 0.010%

    No Known Activations