© 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. 4-CLT-HP
    7. 1760
    Prev
    Next
    INDEX
    Explanations

    saving or rescuing

    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
    +#+#
    -0.68
    HomeAsUpEnabled
    -0.63
    LookAnd
    -0.59
    ագրություններ
    -0.58
    TagMode
    -0.58
    ChromeDriver
    -0.56
     surla
    -0.56
    DebuggerNonUser
    -0.55
    jspx
    -0.55
     مشين
    -0.54
    POSITIVE LOGITS
     embarrassment
    0.68
     involvement
    0.68
     having
    0.65
    noaa
    0.64
     from
    0.59
    having
    0.57
    tedra
    0.57
     trouble
    0.57
     hardship
    0.56
     humiliation
    0.56
    Activations Density 0.009%

    No Known Activations