© 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. 4748
    Prev
    Next
    INDEX
    Explanations

    the

    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
     iprot
    -0.93
    autoIncrement
    -0.76
     <<<<<<<<<<<<<<
    -0.68
     gql
    -0.64
     câte
    -0.61
    urnia
    -0.61
    excellents
    -0.60
     ويكيميديا
    -0.60
    SourceChecksum
    -0.57
    __()
    -0.57
    POSITIVE LOGITS
     past
    0.65
    past
    0.49
     near
    0.48
     beginning
    0.47
    PreferredItem
    0.44
    囗
    0.43
    是因為
    0.43
    过去
    0.40
    sidemargin
    0.40
     future
    0.39
    Activations Density 0.001%

    No Known Activations