© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 46109
    Prev
    Next
    INDEX
    Explanations

    w

    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
     createSlice
    -0.72
    chi
    -0.70
     frontale
    -0.62
    rungsseite
    -0.61
    ]")]
    -0.59
    ########.
    -0.59
    hyrchwyd
    -0.59
     doPost
    -0.57
    ="#"><
    -0.55
    ंदीखरीदारी
    -0.54
    POSITIVE LOGITS
    ništ
    0.52
    RTLR
    0.52
     mijne
    0.47
    GORITH
    0.46
    RTGC
    0.45
    envoy
    0.44
     pleaſure
    0.43
     tena
    0.43
     sideline
    0.43
    CrossRef
    0.42
    Activations Density 0.023%

    No Known Activations