© 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. 3-RES-MATRYOSHKA-DC
    7. 3042
    Prev
    Next
    INDEX
    Explanations

    the word "absence"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -1.00
    +#+#
    -0.98
     للاسماء
    -0.96
    TagMode
    -0.89
    VertexAttrib
    -0.82
    #+#
    -0.81
     TextInputType
    -0.77
    ########.
    -0.75
    providedIn
    -0.73
    Personendaten
    -0.73
    POSITIVE LOGITS
     absence
    2.20
    absence
    1.91
     Absence
    1.91
    Absence
    1.59
     ausencia
    1.53
     absences
    1.38
     absent
    1.19
    Absent
    1.13
    absent
    1.05
     Absent
    1.02
    Activations Density 0.011%

    No Known Activations