© 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. 5-CLT-HP
    7. 93388
    Prev
    Next
    INDEX
    Explanations

    get/start

    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
     betweenstory
    -0.92
    VIAF
    -0.79
    PreferredItem
    -0.79
    verwijspagina
    -0.76
     GetEnumerator
    -0.68
     handleMessage
    -0.66
     snippetHide
    -0.65
    Personensuche
    -0.65
     *++
    -0.64
    aarrggbb
    -0.63
    POSITIVE LOGITS
     Free
    0.55
     free
    0.53
    .​
    0.46
     FREE
    0.46
     prêt
    0.43
     Affordable
    0.42
    Free
    0.42
    TagMode
    0.41
    consulté
    0.41
     Ideas
    0.40
    Activations Density 0.001%

    No Known Activations