© 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. 10274
    Prev
    Next
    INDEX
    Explanations

    acquies

    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
     Joachim
    -0.63
    ineno
    -0.59
    +#+
    -0.59
    Joachim
    -0.52
     pédagogique
    -0.52
    uramente
    -0.50
     ***!
    -0.49
    multer
    -0.49
    RTEE
    -0.48
    脚注の使い方
    -0.48
    POSITIVE LOGITS
    olites
    0.59
    ModelAttribute
    0.58
     հղումներ
    0.56
    thâu
    0.54
    dreaming
    0.53
    íncia
    0.53
    oirs
    0.53
    volent
    0.52
    olite
    0.52
    uscitation
    0.51
    Activations Density 0.017%

    No Known Activations