© 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. 98003
    Prev
    Next
    INDEX
    Explanations

    valley

    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
    ChildScrollView
    -0.56
    parsedMessage
    -0.46
    disposing
    -0.45
    )++;
    -0.44
     třeba
    -0.43
    AnchorTagHelper
    -0.42
    кипе
    -0.41
    antwoorde
    -0.41
    losa
    -0.41
    RenderAtEndOf
    -0.41
    POSITIVE LOGITS
     FetchType
    0.72
     CascadeType
    0.64
    
    0.59
    GraphicsUnit
    0.58
    usermodel
    0.57
     genus
    0.56
    MethodManager
    0.54
    })*/
    0.54
     Code
    0.53
    脚注の使い方
    0.53
    Activations Density 0.000%

    No Known Activations