© 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. 0-CLT-HP
    7. 93789
    Prev
    Next
    INDEX
    Explanations

    Names and code

    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
     esternos
    -0.67
    sung
    -0.67
    ng
    -0.54
    Sung
    -0.54
    pupil
    -0.54
    pup
    -0.54
    EndGlobalSection
    -0.53
     GenerationType
    -0.50
     pupil
    -0.50
     pylori
    -0.50
    POSITIVE LOGITS
     bParam
    0.82
    ſelf
    0.73
    i
    0.73
    ethene
    0.66
     Houſe
    0.66
    xffffffff
    0.65
     ་་
    0.65
    й
    0.64
     Shakspeare
    0.63
     Lepid
    0.63
    Activations Density 1.494%

    No Known Activations