© 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. 5-CLT-HP
    7. 97282
    Prev
    Next
    INDEX
    Explanations

    Actions being completed

    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
    InvalidProtocol
    -0.53
     betweenstory
    -0.51
    MockMvc
    -0.50
     actuels
    -0.50
     normaux
    -0.49
     avven
    -0.47
     internetowa
    -0.47
    MessageOf
    -0.46
    Now
    -0.44
     geslacht
    -0.44
    POSITIVE LOGITS
     there
    0.74
    #+#
    0.68
    Rüyada
    0.64
     by
    0.63
    :+:
    0.59
    imageshack
    0.59
    marvin
    0.55
    there
    0.52
     getItemCount
    0.52
    Nuorodos
    0.51
    Activations Density 0.001%

    No Known Activations