© 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. 4-CLT-HP
    7. 653
    Prev
    Next
    INDEX
    Explanations

    lack of agreement

    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
     agree
    -0.84
    agree
    -0.79
    agreed
    -0.69
     agreeing
    -0.69
     agrees
    -0.68
     Agree
    -0.66
    Agree
    -0.65
     agreed
    -0.63
    consensus
    -0.60
     consensus
    -0.59
    POSITIVE LOGITS
    MLLoader
    0.68
    enumi
    0.63
     autorytatywna
    0.61
    حياته
    0.57
    #
    0.53
     Empieza
    0.52
    حياتها
    0.50
     snippetHide
    0.50
    /**
    0.50
    kloped
    0.49
    Activations Density 0.005%

    No Known Activations