© 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. 4-CLT-HP
    7. 1374
    Prev
    Next
    INDEX
    Explanations

    a/an

    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
    +#+#
    -0.69
    FontOfSize
    -0.66
     TextInputType
    -0.65
    phans
    -0.63
     organist
    -0.62
     vinted
    -0.61
     eaters
    -0.59
    chestra
    -0.59
     Efq
    -0.59
     EdgeInsets
    -0.59
    POSITIVE LOGITS
    ArgsConstructor
    0.75
     Narrative
    0.45
     noDo
    0.43
    чего
    0.42
     then
    0.41
     definitely
    0.41
     Fixed
    0.41
     насељу
    0.41
     Dicapai
    0.41
     wonderful
    0.40
    Activations Density 0.007%

    No Known Activations