© 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. 619
    Prev
    Next
    INDEX
    Explanations

    Referring to previous subjects

    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
     ſtand
    -0.55
     Anſ
    -0.54
     himſelf
    -0.52
     juſ
    -0.50
     abſ
    -0.49
     Houſe
    -0.49
     ſever
    -0.48
     alſo
    -0.47
     Reſ
    -0.47
     purpoſe
    -0.47
    POSITIVE LOGITS
     I
    0.90
     we
    0.80
     you
    0.76
     include
    0.75
     ***!
    0.66
    include
    0.65
    findpost
    0.63
    istoitu
    0.63
    :
    0.62
    ":
    0.61
    Activations Density 0.008%

    No Known Activations