© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1624
    Prev
    Next
    INDEX
    Explanations

    Seeking or providing assistance

    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
     tartalomajánló
    -0.94
    tvguidetime
    -0.93
     المعيارى
    -0.93
    ^(@)
    -0.85
     bezeichneter
    -0.83
     myſelf
    -0.81
    ImageContext
    -0.80
     ExecuteAsync
    -0.78
    Datuak
    -0.78
    Brainz
    -0.78
    POSITIVE LOGITS
    ,
    0.49
     of
    0.47
    .
    0.44
    BeginContext
    0.43
     in
    0.41
     incontra
    0.40
     by
    0.40
    !
    0.39
     ‘
    0.36
    tip
    0.36
    Activations Density 0.005%

    No Known Activations