© 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. 15037
    Prev
    Next
    INDEX
    Explanations

    combinations

    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
     combinations
    -1.42
    combinations
    -1.20
     Combinations
    -1.12
     combination
    -1.00
    combination
    -0.97
     combos
    -0.93
     Combination
    -0.89
     combina
    -0.83
    Combination
    -0.83
     mixtures
    -0.81
    POSITIVE LOGITS
    PerformLayout
    0.58
     surla
    0.57
    abetes
    0.51
     Reverso
    0.50
     spontan
    0.50
    mbals
    0.49
     spont
    0.47
    vindo
    0.45
    ServletException
    0.44
     Gaut
    0.44
    Activations Density 0.014%

    No Known Activations