© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 656
    Prev
    Next
    INDEX
    Explanations

    twice

    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
     aktivitet
    -0.53
     '*')
    -0.47
     or
    -0.47
    ?')
    -0.47
    hamcrest
    -0.46
    nologies
    -0.46
     verksamhet
    -0.46
    gebied
    -0.46
    ználat
    -0.46
    ázat
    -0.45
    POSITIVE LOGITS
    LEncoder
    0.82
    httphttps
    0.70
    WithIOException
    0.65
     noqa
    0.64
     cherchés
    0.64
     TextInputType
    0.64
    RenderAtEndOf
    0.63
    SequentialGroup
    0.62
    enumii
    0.61
    millimeters
    0.61
    Activations Density 0.032%

    No Known Activations