© 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. 5-CLT-HP
    7. 98093
    Prev
    Next
    INDEX
    Explanations

    framework

    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
    tispiece
    -0.49
    enumi
    -0.47
    :+:
    -0.46
    ίος
    -0.44
     plă
    -0.44
    DockStyle
    -0.44
    getBean
    -0.44
    AndEndTag
    -0.44
    SequentialGroup
    -0.43
     corações
    -0.43
    POSITIVE LOGITS
    woff
    0.57
     CommonModule
    0.56
     onAnimation
    0.55
    messageInfo
    0.54
    thebibliography
    0.52
     ICommand
    0.52
     saites
    0.51
     correctes
    0.51
    LoadScene
    0.50
    providedIn
    0.50
    Activations Density 0.030%

    No Known Activations