© 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. 20-CLT-HP
    7. 71692
    Prev
    Next
    INDEX
    Explanations

    Code and file headers

    np_max-act-logits · 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
    Hentet
    -0.70
     MainAxisSize
    -0.65
    ConstraintMaker
    -0.64
     كومونز
    -0.61
     cherchés
    -0.60
    Бахар
    -0.59
     defaultstate
    -0.59
     snippetHide
    -0.59
    .');
    -0.59
    béco
    -0.57
    POSITIVE LOGITS
    onViewCreated
    0.51
    hilangan
    0.47
     fermés
    0.44
     carrés
    0.43
     supérieurs
    0.42
     définiti
    0.41
    piles
    0.41
     scolaires
    0.40
     répondit
    0.40
    ologies
    0.39
    Activations Density 0.002%

    No Known Activations