© 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. 3969
    Prev
    Next
    INDEX
    Explanations

    design

    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
    astify
    -0.46
    jsonwebtoken
    -0.44
    ❋
    -0.43
     junctions
    -0.42
    UrlEncoded
    -0.42
    iteiten
    -0.41
     connections
    -0.41
     workings
    -0.40
    URLConnection
    -0.40
    colgroup
    -0.40
    POSITIVE LOGITS
    technique
    0.75
     prisonniers
    0.73
     technique
    0.71
     BoxDecoration
    0.68
    úsqueda
    0.66
     gevolg
    0.65
     idiom
    0.64
    DebuggerNonUser
    0.64
     mogelijkheid
    0.63
    InjectMocks
    0.61
    Activations Density 0.001%

    No Known Activations