© 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. 93731
    Prev
    Next
    INDEX
    Explanations

    travel surfaces

    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
    AddTagHelper
    -0.81
    aryen
    -0.69
    QObject
    -0.62
    ]")]
    -0.60
    InstanceState
    -0.58
    providedIn
    -0.57
    XmlAccessType
    -0.56
     ddelweddau
    -0.54
    FilterChain
    -0.54
    ScopeManager
    -0.52
    POSITIVE LOGITS
    approach
    0.57
     approach
    0.56
    Approach
    0.53
     BorderSide
    0.52
     dehors
    0.52
     APPROACH
    0.52
     Approach
    0.51
    zzleHttp
    0.51
     outside
    0.51
    eabouts
    0.50
    Activations Density 0.004%

    No Known Activations