© 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. 5-CLT-HP
    7. 4770
    Prev
    Next
    INDEX
    Explanations

    Instructions/Suggestions

    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
     kelapa
    -0.55
    OGND
    -0.53
     består
    -0.52
    rooms
    -0.50
    inspire
    -0.50
    Dij
    -0.48
    そして
    -0.48
    ELEMENT
    -0.47
     officielles
    -0.47
     된
    -0.47
    POSITIVE LOGITS
     finding
    0.70
     figuring
    0.68
     discovering
    0.68
     getting
    0.65
     using
    0.64
     having
    0.63
     knowing
    0.63
     Normdatei
    0.62
     deciding
    0.62
     installing
    0.62
    Activations Density 0.001%

    No Known Activations