© 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. 0-CLT-HP
    7. 95312
    Prev
    Next
    INDEX
    Explanations

    clusion

    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
     secured
    -0.83
    secured
    -0.77
     secure
    -0.77
     wrap
    -0.76
    clusion
    -0.69
     Wrap
    -0.68
     securing
    -0.67
    clude
    -0.66
     wraps
    -0.66
     Concluding
    -0.66
    POSITIVE LOGITS
    IANGLES
    0.67
    VersionUID
    0.66
    Hozzáférés
    0.65
     مشين
    0.65
    verwijspagina
    0.65
    ']]
    0.65
    fjspx
    0.65
    PreferredItem
    0.65
    )]
    0.64
    etCode
    0.63
    Activations Density 1.523%

    No Known Activations