© 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. 1-CLT-HP
    7. 15308
    Prev
    Next
    INDEX
    Explanations

    resources

    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
     resources
    -1.31
     resource
    -1.30
     Resource
    -1.13
    resource
    -1.11
    resources
    -1.09
    Resource
    -1.09
     Resources
    -1.07
     RESOURCES
    -1.06
     ressources
    -1.02
    Resources
    -1.00
    POSITIVE LOGITS
     poveznice
    0.65
    complexType
    0.65
    ParallelGroup
    0.62
    SequentialGroup
    0.60
    ApiModelProperty
    0.56
    jsxFileName
    0.55
    adaptiveStyles
    0.55
    __(/*!
    0.53
    :✨
    0.53
     CWE
    0.51
    Activations Density 0.015%

    No Known Activations