© 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. 1-CLT-HP
    7. 13816
    Prev
    Next
    INDEX
    Explanations

    horse

    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
    orte
    -0.50
     Hen
    -0.49
    (!__
    -0.48
     verra
    -0.47
    Hen
    -0.46
     sveta
    -0.46
     côtés
    -0.46
     indios
    -0.45
    tit
    -0.45
    PEAT
    -0.45
    POSITIVE LOGITS
     становника
    0.69
     Normdatei
    0.65
    })*/
    0.64
    WritableDatabase
    0.63
    }}/>
    0.62
    }{*}{}
    0.61
    Londres
    0.60
     resourceCulture
    0.60
    izable
    0.59
    forKey
    0.59
    Activations Density 0.012%

    No Known Activations