© 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. 52
    Prev
    Next
    INDEX
    Explanations

    located

    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
    Kariera
    -0.53
    ίων
    -0.51
    SwingConstants
    -0.50
    webElementXpaths
    -0.49
    ius
    -0.49
     pinulongan
    -0.48
     BoxFit
    -0.48
    SequentialGroup
    -0.47
    lgari
    -0.47
    جغرافيا
    -0.46
    POSITIVE LOGITS
    <bos>
    0.75
    verwijspagina
    0.63
    ]")]
    0.60
     between
    0.59
     itſelf
    0.58
     juſt
    0.57
     كومونز
    0.56
     about
    0.56
    AnchorStyles
    0.55
    felves
    0.54
    Activations Density 0.002%

    No Known Activations