© 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. 1-CLT-HP
    7. 13881
    Prev
    Next
    INDEX
    Explanations

    )

    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
     avoient
    -0.95
     auroit
    -0.92
     feroit
    -0.89
     étoit
    -0.84
     étoient
    -0.83
     pouvoit
    -0.80
     verksamhet
    -0.75
     fermés
    -0.74
     réflex
    -0.72
     leçons
    -0.71
    POSITIVE LOGITS
     صوتيه
    0.74
    ImageContext
    0.72
     however
    0.72
    ContentAsync
    0.67
     therefore
    0.65
     while
    0.63
     snippetHide
    0.60
     jsPsych
    0.59
     since
    0.58
    exitRule
    0.58
    Activations Density 0.029%

    No Known Activations