© 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. 1-CLT-HP
    7. 10171
    Prev
    Next
    INDEX
    Explanations

    repeated action

    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
     again
    -0.84
    Again
    -0.81
     Again
    -0.77
    again
    -0.73
     novamente
    -0.65
     AGAIN
    -0.64
     опять
    -0.60
     ponownie
    -0.60
    encodeWith
    -0.60
     دوباره
    -0.58
    POSITIVE LOGITS
     nakalista
    0.67
    édrale
    0.55
    med
    0.49
    üyada
    0.47
    Datuak
    0.47
    ElementException
    0.46
     présence
    0.45
    PYX
    0.44
    SuspendLayout
    0.44
    aged
    0.44
    Activations Density 1.081%

    No Known Activations